receiving-code-review
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Skill contract explicitly requires “Incoming review feedback (PR comments, verbal review notes)” to be read by the agent at runtime (i.e., free-form text authored by external reviewers), which can flow into the agent’s LLM context for evaluation and response.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata