Vulnerability-Lookup

CVE-2026-53710 (GCVE-0-2026-53710)

Vulnerability from cvelistv5 – Published: 2026-09-15 16:47 – Updated: 2026-09-15 19:45

Title

MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server

Summary

MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2.

Severity

10 (Critical)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

SSVC

Exploitation: none Automatable: yes Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-09-15 19:16 UTC

CWE

CWE-94 - Improper Control of Generation of Code ('Code Injection')
CWE-693 - Protection Mechanism Failure

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7958 records in the last 180 days details

References

3 references

URL	Tags
https://github.com/IBM/mcp-context-forge/security…	x_refsource_CONFIRM
https://github.com/IBM/mcp-context-forge/commit/6…	x_refsource_MISC
https://github.com/IBM/mcp-context-forge/releases…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version	CPE status
IBM	mcp-context-forge	Affected: < 1.0.2	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-53710",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-15T19:16:37.898454Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-15T19:45:23.818Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "mcp-context-forge",
          "vendor": "IBM",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.0.2"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 10,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-693",
              "description": "CWE-693: Protection Mechanism Failure",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-15T16:47:41.085Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
        },
        {
          "name": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
        },
        {
          "name": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2"
        }
      ],
      "source": {
        "advisory": "GHSA-xm98-3vcf-fph7",
        "discovery": "UNKNOWN"
      },
      "title": "MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-53710",
    "datePublished": "2026-09-15T16:47:41.085Z",
    "dateReserved": "2026-06-10T16:43:31.241Z",
    "dateUpdated": "2026-09-15T19:45:23.818Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-53710",
      "date": "2026-11-08",
      "epss": "0.01141",
      "percentile": "0.66877"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "mcp-context-forge",
                "vendor": "IBM",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 1.0.2"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2."
          }
        ],
        "id": "CVE-2026-53710",
        "lastModified": "2026-09-30T17:51:56.193",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 10.0,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 6.0,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-53710",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-15T19:16:37.898454Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-09-15T17:17:19.117",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Deferred",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-94"
              },
              {
                "lang": "en",
                "value": "CWE-693"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-53710",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T19:16:37.898454Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T19:16:39.303Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "mcp-context-forge",
              "vendor": "IBM",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 1.0.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 10,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-94",
                  "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T16:47:41.085Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
            },
            {
              "name": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
            },
            {
              "name": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2"
            }
          ],
          "source": {
            "advisory": "GHSA-xm98-3vcf-fph7",
            "discovery": "UNKNOWN"
          },
          "title": "MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-53710",
        "datePublished": "2026-09-15T16:47:41.085Z",
        "dateReserved": "2026-06-10T16:43:31.241Z",
        "dateUpdated": "2026-09-15T19:45:23.818Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-53710

Vulnerability from fkie_nvd - Published: 2026-09-15 17:17 - Updated: 2026-09-30 17:51

Severity

10.0 (Critical) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89
	security-advisories@github.com	https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2
	security-advisories@github.com	https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "mcp-context-forge",
          "vendor": "IBM",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.0.2"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2."
    }
  ],
  "id": "CVE-2026-53710",
  "lastModified": "2026-09-30T17:51:56.193",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 10.0,
          "baseSeverity": "CRITICAL",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "CHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 6.0,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-53710",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-09-15T19:16:37.898454Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-09-15T17:17:19.117",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        },
        {
          "lang": "en",
          "value": "CWE-693"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-XM98-3VCF-FPH7

Vulnerability from github – Published: 2026-08-24 19:20 – Updated: 2026-09-02 15:28

Summary

mcp-contextforge-gateway has RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server

Details

Commit: f855e54d5b7bc1c91b977574a03b91eff6b86bb6 Component: mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py

Vulnerability

RestrictedPython's sandbox in ContextForge's python_sandbox_server sub-project allows arbitrary Python execution via three compounding weaknesses:

Raw getattr is exposed in safe_builtins, bypassing _getattr_ mediation.
validate_code checks for literal dangerous dunder strings, but the payload constructs those names at runtime.
The execute_code MCP tool can be exposed over HTTP/SSE transport with no authentication layer.

Proof of Concept

The local PoC was executed against the real pinned sandbox code path. It constructs dunder names at runtime, walks Python's class hierarchy through the exposed getattr, finds subprocess.Popen, and executes a harmless marker command.

Transcript excerpt:

POC: IBM/mcp-context-forge RestrictedPython getattr sandbox bypass
validation={'valid': True, 'message': 'Code passed validation', 'warnings': None}
success=True
stdout="FOUND_POPEN\nb'IBM_SANDBOX_POC_PASS'\n"
IBM_RESTRICTEDPYTHON_GETATTR_POPEN_REPRO_PASS

PoC artifact hashes:

beb2d856c5a1b7c10005c9c0fccaf3d491d4fbcc2a69bc54b5e95c5730c0874b  run.py
1037dcb4f0831a3c96ca728527f939af1d3e19514b23ef54f663707875748ff8  run.sh
7026e676ee31916886f10feed959ffdbe486fda05b17421387e4717acbf90ba6  transcript.txt

Production Deployment Context

ContextForge's documentation describes registering MCP servers as gateways in a running ContextForge instance. If this sandbox server is reachable over HTTP in that pattern, any client that can reach the endpoint can submit the payload through tools/call.

Impact

An attacker with access to the python_sandbox_server HTTP endpoint can execute OS commands with the privileges of the server process. In containerized deployments with host mounts or internal network reachability, this can become filesystem compromise or network pivoting from the gateway host.

Suggested Fix

Remove raw getattr and setattr from safe_builtins, expose only policy-controlled attribute access if dynamic lookup is required, replace substring filtering with a stricter RestrictedPython policy pipeline, and add authentication to HTTP transport for all tools/call requests.

Caveats

This report covers the python_sandbox_server sub-project. The core ContextForge gateway and proxy components are not directly affected. The Critical score assumes HTTP reachability; stdio-only deployments reduce the attack vector.

Severity

10.0 (Critical)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 1.0.1"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "mcp-contextforge-gateway"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.0.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-53710"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-693",
      "CWE-94"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-08-24T19:20:58Z",
    "nvd_published_at": null,
    "severity": "CRITICAL"
  },
  "details": "**Commit:** `f855e54d5b7bc1c91b977574a03b91eff6b86bb6`\n**Component:** `mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py`\n\n## Vulnerability\n\nRestrictedPython\u0027s sandbox in ContextForge\u0027s `python_sandbox_server` sub-project allows arbitrary Python execution via three compounding weaknesses:\n\n1. Raw `getattr` is exposed in `safe_builtins`, bypassing `_getattr_` mediation.\n2. `validate_code` checks for literal dangerous dunder strings, but the payload constructs those names at runtime.\n3. The `execute_code` MCP tool can be exposed over HTTP/SSE transport with no authentication layer.\n\n## Proof of Concept\n\nThe local PoC was executed against the real pinned sandbox code path. It constructs dunder names at runtime, walks Python\u0027s class hierarchy through the exposed `getattr`, finds `subprocess.Popen`, and executes a harmless marker command.\n\nTranscript excerpt:\n\n```text\nPOC: IBM/mcp-context-forge RestrictedPython getattr sandbox bypass\nvalidation={\u0027valid\u0027: True, \u0027message\u0027: \u0027Code passed validation\u0027, \u0027warnings\u0027: None}\nsuccess=True\nstdout=\"FOUND_POPEN\\nb\u0027IBM_SANDBOX_POC_PASS\u0027\\n\"\nIBM_RESTRICTEDPYTHON_GETATTR_POPEN_REPRO_PASS\n```\n\nPoC artifact hashes:\n\n```text\nbeb2d856c5a1b7c10005c9c0fccaf3d491d4fbcc2a69bc54b5e95c5730c0874b  run.py\n1037dcb4f0831a3c96ca728527f939af1d3e19514b23ef54f663707875748ff8  run.sh\n7026e676ee31916886f10feed959ffdbe486fda05b17421387e4717acbf90ba6  transcript.txt\n```\n\n## Production Deployment Context\n\nContextForge\u0027s documentation describes registering MCP servers as gateways in a running ContextForge instance. If this sandbox server is reachable over HTTP in that pattern, any client that can reach the endpoint can submit the payload through `tools/call`.\n\n## Impact\n\nAn attacker with access to the `python_sandbox_server` HTTP endpoint can execute OS commands with the privileges of the server process. In containerized deployments with host mounts or internal network reachability, this can become filesystem compromise or network pivoting from the gateway host.\n\n## Suggested Fix\n\nRemove raw `getattr` and `setattr` from `safe_builtins`, expose only policy-controlled attribute access if dynamic lookup is required, replace substring filtering with a stricter RestrictedPython policy pipeline, and add authentication to HTTP transport for all `tools/call` requests.\n\n## Caveats\n\nThis report covers the `python_sandbox_server` sub-project. The core ContextForge gateway and proxy components are not directly affected. The Critical score assumes HTTP reachability; stdio-only deployments reduce the attack vector.",
  "id": "GHSA-xm98-3vcf-fph7",
  "modified": "2026-09-02T15:28:19Z",
  "published": "2026-08-24T19:20:58Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
    },
    {
      "type": "WEB",
      "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/IBM/mcp-context-forge"
    },
    {
      "type": "WEB",
      "url": "https://github.com/IBM/mcp-context-forge/releases#release-v1.0.2"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "mcp-contextforge-gateway has RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server"
}

PYSEC-2026-3862

Vulnerability from pysec - Published: 2026-09-10 09:44 - Updated: 2026-09-10 11:02

Details

Commit: f855e54d5b7bc1c91b977574a03b91eff6b86bb6 Component: mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py

Vulnerability

RestrictedPython's sandbox in ContextForge's python_sandbox_server sub-project allows arbitrary Python execution via three compounding weaknesses:

Raw getattr is exposed in safe_builtins, bypassing _getattr_ mediation.
validate_code checks for literal dangerous dunder strings, but the payload constructs those names at runtime.
The execute_code MCP tool can be exposed over HTTP/SSE transport with no authentication layer.

Proof of Concept

Transcript excerpt:

POC: IBM/mcp-context-forge RestrictedPython getattr sandbox bypass
validation={'valid': True, 'message': 'Code passed validation', 'warnings': None}
success=True
stdout="FOUND_POPEN\nb'IBM_SANDBOX_POC_PASS'\n"
IBM_RESTRICTEDPYTHON_GETATTR_POPEN_REPRO_PASS

PoC artifact hashes:

beb2d856c5a1b7c10005c9c0fccaf3d491d4fbcc2a69bc54b5e95c5730c0874b  run.py
1037dcb4f0831a3c96ca728527f939af1d3e19514b23ef54f663707875748ff8  run.sh
7026e676ee31916886f10feed959ffdbe486fda05b17421387e4717acbf90ba6  transcript.txt

Production Deployment Context

Impact

Suggested Fix

Caveats

Severity

10.0 (Critical)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Impacted products

Name	purl
mcp-contextforge-gateway	pkg:pypi/mcp-contextforge-gateway

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "mcp-contextforge-gateway",
        "purl": "pkg:pypi/mcp-contextforge-gateway"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.0.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.1.0",
        "0.1.1",
        "0.2.0",
        "0.3.0",
        "0.3.1",
        "0.4.0",
        "0.5.0",
        "0.6.0",
        "0.7.0",
        "0.8.0",
        "0.9.0",
        "1.0.0",
        "1.0.0b1",
        "1.0.0b2",
        "1.0.0rc1",
        "1.0.1"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-53710",
    "GHSA-xm98-3vcf-fph7"
  ],
  "details": "**Commit:** `f855e54d5b7bc1c91b977574a03b91eff6b86bb6`\n**Component:** `mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py`\n\n## Vulnerability\n\nRestrictedPython\u0027s sandbox in ContextForge\u0027s `python_sandbox_server` sub-project allows arbitrary Python execution via three compounding weaknesses:\n\n1. Raw `getattr` is exposed in `safe_builtins`, bypassing `_getattr_` mediation.\n2. `validate_code` checks for literal dangerous dunder strings, but the payload constructs those names at runtime.\n3. The `execute_code` MCP tool can be exposed over HTTP/SSE transport with no authentication layer.\n\n## Proof of Concept\n\nThe local PoC was executed against the real pinned sandbox code path. It constructs dunder names at runtime, walks Python\u0027s class hierarchy through the exposed `getattr`, finds `subprocess.Popen`, and executes a harmless marker command.\n\nTranscript excerpt:\n\n```text\nPOC: IBM/mcp-context-forge RestrictedPython getattr sandbox bypass\nvalidation={\u0027valid\u0027: True, \u0027message\u0027: \u0027Code passed validation\u0027, \u0027warnings\u0027: None}\nsuccess=True\nstdout=\"FOUND_POPEN\\nb\u0027IBM_SANDBOX_POC_PASS\u0027\\n\"\nIBM_RESTRICTEDPYTHON_GETATTR_POPEN_REPRO_PASS\n```\n\nPoC artifact hashes:\n\n```text\nbeb2d856c5a1b7c10005c9c0fccaf3d491d4fbcc2a69bc54b5e95c5730c0874b  run.py\n1037dcb4f0831a3c96ca728527f939af1d3e19514b23ef54f663707875748ff8  run.sh\n7026e676ee31916886f10feed959ffdbe486fda05b17421387e4717acbf90ba6  transcript.txt\n```\n\n## Production Deployment Context\n\nContextForge\u0027s documentation describes registering MCP servers as gateways in a running ContextForge instance. If this sandbox server is reachable over HTTP in that pattern, any client that can reach the endpoint can submit the payload through `tools/call`.\n\n## Impact\n\nAn attacker with access to the `python_sandbox_server` HTTP endpoint can execute OS commands with the privileges of the server process. In containerized deployments with host mounts or internal network reachability, this can become filesystem compromise or network pivoting from the gateway host.\n\n## Suggested Fix\n\nRemove raw `getattr` and `setattr` from `safe_builtins`, expose only policy-controlled attribute access if dynamic lookup is required, replace substring filtering with a stricter RestrictedPython policy pipeline, and add authentication to HTTP transport for all `tools/call` requests.\n\n## Caveats\n\nThis report covers the `python_sandbox_server` sub-project. The core ContextForge gateway and proxy components are not directly affected. The Critical score assumes HTTP reachability; stdio-only deployments reduce the attack vector.",
  "id": "PYSEC-2026-3862",
  "modified": "2026-09-10T11:02:13.975963Z",
  "published": "2026-09-10T09:44:53.257579Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7"
    },
    {
      "type": "WEB",
      "url": "https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/IBM/mcp-context-forge"
    },
    {
      "type": "WEB",
      "url": "https://github.com/IBM/mcp-context-forge/releases#release-v1.0.2"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/mcp-contextforge-gateway"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-xm98-3vcf-fph7"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-53710"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "mcp-contextforge-gateway has RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

CVE-2026-53710 (GCVE-0-2026-53710)

FKIE_CVE-2026-53710

GHSA-XM98-3VCF-FPH7

Vulnerability

Proof of Concept

Production Deployment Context

Impact

Suggested Fix

Caveats

PYSEC-2026-3862

Vulnerability

Proof of Concept

Production Deployment Context

Impact

Suggested Fix

Caveats

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour