gh-treasure-hunt

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

• Third-party content exposure detected (high risk: 0.85). The workflow pulls and then ingests outsider-authored free text from GitHub PR/issue bodies/comments via gh pr view / gh pr checks / gh issue list (and related fields), which are untrusted outsider content that can be included in the agent’s LLM context during “confirm each shortlisted PR from code, tests, comments, and checks.”