{
  "id": "ghsl-2026-180",
  "title": "GitHub gh-aw MCP argument injection can bypass intended command safeguards",
  "product": "GitHub gh-aw CLI and MCP server",
  "ai_system": "GitHub Security Lab Taskflow Agent",
  "organization": "GitHub Security Lab and GitHub",
  "summary": "In gh-aw versions before v0.91.12, MCP handlers appended untrusted client strings into child-process argv without a `--` separator or leading-hyphen rejection. A lower-trust MCP client could inject supported flags to bypass workflow security controls and perform credential-backed GitHub operations. GHSL assigns identifier GHSL-2026-180 and the repository advisory GHSA-f7r8-5pqp-q5p4; no CVE is assigned.",
  "ai_role": "The published repository advisory explicitly says Taskflow Agent discovered the issue and GHSL manually verified it. It identifies the AI system and human verification separately; no priority claim is needed.",
  "disclosure_date": "2026-10-14",
  "ai_attribution_date": "2026-10-14",
  "classification": "pre-release",
  "classification_note": "The advisory says the fix was included in v0.91.12 published October 14, 2026; that version is marked pre-release.",
  "cves": [],
  "source_url": "https://github.com/github/gh-aw/security/advisories/GHSA-f7r8-5pqp-q5p4",
  "ai_source_url": "https://github.com/github/gh-aw/security/advisories/GHSA-f7r8-5pqp-q5p4",
  "remediation": "fix documented",
  "remediation_note": "Patched in gh-aw v0.91.12, published October 14, 2026 and marked pre-release. The advisory recommends v0.91.12 or later; downstream deployment is not verified.",
  "advisory_url": "https://github.com/github/gh-aw/security/advisories/GHSA-f7r8-5pqp-q5p4",
  "checked_date": "2026-11-14",
  "impacts": [
    {
      "cves": [],
      "consequences": [
        "data modification",
        "other"
      ],
      "conditions": "A less-trusted MCP client able to reach the local server can inject argv flags that bypass intended restrictions, perform GitHub writes (push branches/open PRs), disable scanners, alter workflows/lock files, and write outside `.github/workflows`. The advisory also says a specific `mcp-inspect` argument can launch the MCP Inspector via npx; it does not establish arbitrary attacker-chosen code execution.",
      "exploitation": "The advisory confirms the argv-parsing primitive; it does not establish exploitation in the wild.",
      "source_url": "https://github.com/github/gh-aw/security/advisories/GHSA-f7r8-5pqp-q5p4",
      "checked_date": "2026-11-16"
    }
  ]
}
