ci-feedback-loop

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the skill downloads GitHub Actions run logs/artifacts from the public GitHub Actions API (via gh api .../actions/runs/<run_id>/logs and gh run download ...), then extracts/reads the resulting .txt/.log contents and prints them into the agent’s LLM context.