coderabbit-security-basics
Warn
Audited by Snyk on Apr 4, 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 ingests and acts on user-generated GitHub PR diffs and PR comments (see "Step 2: Secret Detection with GitHub Integration" and "Step 3: Security Review Learnings" in SKILL.md), which are untrusted third-party inputs that can train the agent and materially change its future behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata