pr-autopilot
Warn
Audited by Snyk on Jun 13, 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). Outsider free text can enter the LLM context via Step 1’s “fetch all three sources” from GitHub PR review/comment threads (e.g., issue/PR comment bodies and review text authored by other users/bots), which the skill then triages/classifies and uses to generate replies.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata