pr-guardian
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). At runtime the workflow step “Check the initial PR state with
gh pr view,gh pr checks, and recent comments or review threads” and later “Inspect agent, bot, and human feedback on the PR” will ingest outsider-authored free text from PR comments/review threads (i.e., text written by other users/bots on the PR) into the agent’s LLM context via the GitHub CLI/API.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata