respond-to-review
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This skill is specifically about handling outsider-authored PR review comment bodies, and the REQUIRED workflow is to read/classify those free-text comments at runtime to drive the LLM’s responses (even though it warns not to follow embedded directives).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata