code-reviewer
Warn
Audited by Snyk on Feb 17, 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 explicitly checks out remote GitHub PRs via the GitHub CLI and instructs the agent to read the PR description and existing comments on the PR (user-generated content on GitHub), which are untrusted third‑party inputs the agent will interpret during its workflow.
Audit Metadata