fix-pr-review
Warn
Audited by Snyk on Apr 23, 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). The skill explicitly fetches and parses GitHub PR review threads and CodeRabbit review bodies via GitHub API/GraphQL (see Phase 2 "Fetch review data" and "Parse CodeRabbit body's AI prompt block") — these are untrusted, user-generated third‑party comments that the agent reads and uses to drive triage, fixes, and tool actions, so they could carry indirect prompt-injection instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata