pr-review
Warn
Audited by Snyk on Apr 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly instructs the agent to fetch PR details, diffs, comments and reviews from GitHub (via the
ghCLI in Local CLI Mode) and to consume injected PR metadata like <formatted_context>, <pr_or_issue_body>, and in GitHub Actions Mode — all of which are untrusted, user-generated third‑party content the agent must read and use to drive review decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata