pr-respond
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill ingests prior
pr-feedbacktriage from the conversation (which can include outsider-authored PR review/comment text) and then posts replies/reactions via GitHub APIs; this runtime LLM context can therefore include free-form outsider text from those review items.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata