review-crdb
Warn
Audited by Snyk on Mar 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and ingest PR diffs and PR metadata from GitHub (e.g., "gh pr diff ", "gh pr view ", "Each agent receives: The diff (or file list) to review") and to post reviews via the GitHub API, which means untrusted, user-generated PR content is read and directly influences the agent's review decisions and tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata