github-workflow

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill ingests and interprets user-generated repository and CI data (e.g., actions/checkout + git diff, npm audit / pip-audit results written to security-results.json, and gh run view --log / gh run view --json job outputs), which are third-party/untrusted content the agent parses as part of its workflow.