greptile-address
Warn
Audited by Snyk on May 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests PR descriptions, Greptile review comments, and inline review threads via GitHub API calls (see SKILL.md steps 3–4 using "gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews" and comments and the instruction to "Read only the Greptile Summary (in the PR description...)" ), which are untrusted/user-generated third‑party content and are used to decide fixes, resolve threads, and drive actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata