respond-to-review
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 REQUIRED workflow ingests Elixir/Phoenix PR review comments (outsider-authored free text) at runtime via the “code-review” predecessor, and then reads/classifies them before responding, creating indirect prompt-injection exposure through that comment text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata