Vulnerability-Lookup

GHSA-8X83-862F-C85R

Vulnerability from github – Published: 2026-08-26 18:31 – Updated: 2026-08-26 18:31

Details

Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.

Severity

9.2 (Critical)


                  
                    CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-75062"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-95"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-08-26T15:16:55Z",
    "severity": "CRITICAL"
  },
  "details": "Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027) in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.",
  "id": "GHSA-8x83-862f-c85r",
  "modified": "2026-08-26T18:31:55Z",
  "published": "2026-08-26T18:31:55Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-75062"
    },
    {
      "type": "WEB",
      "url": "https://github.com/google/langfun/issues/725"
    },
    {
      "type": "WEB",
      "url": "https://github.com/google/langfun"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-75062 (GCVE-0-2026-75062)

Vulnerability from cvelistv5 – Published: 2026-08-26 14:50 – Updated: 2026-08-27 16:55

Title

Eval Injection in google/langfun via default lf.query protocol

Summary

Severity

9.2 (Critical)


                        
                          CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

SSVC

Exploitation: poc Automatable: no Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-08-26 15:37 UTC

CWE

CWE-95 - Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
CWE-1188 - Insecure Default Initialization of Resource

Assigner

Google CNA under the Google root

CNA scorecard C 75/100 over 33 records in the last 180 days details

References

2 references

URL	Tags
https://github.com/google/langfun	product
https://github.com/google/langfun/issues/725	issue-tracking

Impacted products

1 product

Vendor	Product	Version
Google	langfun	Affected: 0.0.1 , < 0.1.2 (semver)

Credits

Hamza Haroon

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-75062",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-26T15:37:45.461767Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-26T15:38:02.455Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/google/langfun/issues/725"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageName": "langfun",
          "product": "langfun",
          "repo": "https://github.com/google/langfun",
          "vendor": "Google",
          "versions": [
            {
              "lessThan": "0.1.2",
              "status": "affected",
              "version": "0.0.1",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Hamza Haroon"
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "\u003cp\u003eImproper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027) in the default \u003ccode\u003elf.query\u003c/code\u003e Python protocol in Google \u003ccode\u003elangfun\u003c/code\u003e versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.\u003c/p\u003e"
            }
          ],
          "value": "Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027) in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox."
        }
      ],
      "impacts": [
        {
          "capecId": "CAPEC-242",
          "descriptions": [
            {
              "lang": "en",
              "value": "CAPEC-242: Code Injection"
            }
          ]
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 9.2,
            "baseSeverity": "CRITICAL",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-95",
              "description": "CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-1188",
              "description": "CWE-1188: Insecure Default Initialization of Resource",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-27T16:55:00.832Z",
        "orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
        "shortName": "Google"
      },
      "references": [
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/google/langfun"
        },
        {
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/google/langfun/issues/725"
        }
      ],
      "source": {
        "discovery": "EXTERNAL"
      },
      "title": "Eval Injection in google/langfun via default lf.query protocol",
      "x_generator": {
        "engine": "Vulnogram 1.0.4"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
    "assignerShortName": "Google",
    "cveId": "CVE-2026-75062",
    "datePublished": "2026-08-26T14:50:50.604Z",
    "dateReserved": "2026-08-17T15:35:22.670Z",
    "dateUpdated": "2026-08-27T16:55:00.832Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

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

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