GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration
Search

Find a vulnerability

Search criteria

    2 vulnerabilities found for qwed-mcp by QWED-AI

    CVE-2026-55546 (GCVE-0-2026-55546)

    Vulnerability from nvd – Published: 2026-08-25 15:25 – Updated: 2026-08-25 18:26
    VLAI
    Title
    QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input
    Summary
    QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy's parse_expr() after only normalizing caret syntax to Python exponent syntax, without restricting global_dict, removing Python built-ins, or validating the expression AST. Because parse_expr() calls Python's eval() with built-ins available, an attacker who can cause a downstream caller to pass untrusted input to this public library function can use Python import functionality to execute arbitrary operating-system commands as the qwed-mcp process user, read or modify accessible data, exfiltrate process secrets, or reach internal services. The default MCP tool registry does not expose verify_math_expression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-08-25 18:26 UTC
    CWE
    • CWE-94 - Improper Control of Generation of Code ('Code Injection')
    Impacted products
    Vendor Product Version
    QWED-AI qwed-mcp Affected: < 0.2.1
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-55546",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-25T18:26:37.346015Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-25T18:26:44.049Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "qwed-mcp",
              "vendor": "QWED-AI",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.2.1"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy\u0027s parse_expr() after only normalizing caret syntax to Python exponent syntax, without restricting global_dict, removing Python built-ins, or validating the expression AST. Because parse_expr() calls Python\u0027s eval() with built-ins available, an attacker who can cause a downstream caller to pass untrusted input to this public library function can use Python import functionality to execute arbitrary operating-system commands as the qwed-mcp process user, read or modify accessible data, exfiltrate process secrets, or reach internal services. The default MCP tool registry does not expose verify_math_expression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/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"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-25T15:25:34.759Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2"
            },
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/pull/22",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/pull/22"
            },
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/commit/362e61892052e250c56cb1ee852024d6f98c467b",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/commit/362e61892052e250c56cb1ee852024d6f98c467b"
            },
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/releases/tag/v0.2.1",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/releases/tag/v0.2.1"
            }
          ],
          "source": {
            "advisory": "GHSA-mw6r-2hvm-4rp2",
            "discovery": "UNKNOWN"
          },
          "title": "QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-55546",
        "datePublished": "2026-08-25T15:25:34.759Z",
        "dateReserved": "2026-06-16T23:01:04.075Z",
        "dateUpdated": "2026-08-25T18:26:44.049Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-55546 (GCVE-0-2026-55546)

    Vulnerability from cvelistv5 – Published: 2026-08-25 15:25 – Updated: 2026-08-25 18:26
    VLAI
    Title
    QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input
    Summary
    QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy's parse_expr() after only normalizing caret syntax to Python exponent syntax, without restricting global_dict, removing Python built-ins, or validating the expression AST. Because parse_expr() calls Python's eval() with built-ins available, an attacker who can cause a downstream caller to pass untrusted input to this public library function can use Python import functionality to execute arbitrary operating-system commands as the qwed-mcp process user, read or modify accessible data, exfiltrate process secrets, or reach internal services. The default MCP tool registry does not expose verify_math_expression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-08-25 18:26 UTC
    CWE
    • CWE-94 - Improper Control of Generation of Code ('Code Injection')
    Impacted products
    Vendor Product Version
    QWED-AI qwed-mcp Affected: < 0.2.1
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-55546",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-25T18:26:37.346015Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-25T18:26:44.049Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "qwed-mcp",
              "vendor": "QWED-AI",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.2.1"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy\u0027s parse_expr() after only normalizing caret syntax to Python exponent syntax, without restricting global_dict, removing Python built-ins, or validating the expression AST. Because parse_expr() calls Python\u0027s eval() with built-ins available, an attacker who can cause a downstream caller to pass untrusted input to this public library function can use Python import functionality to execute arbitrary operating-system commands as the qwed-mcp process user, read or modify accessible data, exfiltrate process secrets, or reach internal services. The default MCP tool registry does not expose verify_math_expression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/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"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-25T15:25:34.759Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2"
            },
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/pull/22",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/pull/22"
            },
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/commit/362e61892052e250c56cb1ee852024d6f98c467b",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/commit/362e61892052e250c56cb1ee852024d6f98c467b"
            },
            {
              "name": "https://github.com/QWED-AI/qwed-mcp/releases/tag/v0.2.1",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/QWED-AI/qwed-mcp/releases/tag/v0.2.1"
            }
          ],
          "source": {
            "advisory": "GHSA-mw6r-2hvm-4rp2",
            "discovery": "UNKNOWN"
          },
          "title": "QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-55546",
        "datePublished": "2026-08-25T15:25:34.759Z",
        "dateReserved": "2026-06-16T23:01:04.075Z",
        "dateUpdated": "2026-08-25T18:26:44.049Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }