code-reviewer
Warn
Audited by Snyk on Jun 22, 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). The skill’s runtime review input is the operating user’s chosen PR/issue/wiki text (outsider-authored content) that the agent will read and include in the LLM context; SKILL.md itself doesn’t show the ingestion mechanism, but the “Review pull requests / security audits” workflow necessarily consumes outsider-authored free-form code/comments from those artifacts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata