pr-autopilot
Warn
Audited by Snyk on Jul 24, 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 required workflow fetches PR comment/review text (and CI failure logs) from outside the operating user via GitHub APIs during Step 1 polling, which becomes untrusted readable prose in the agent context; this is classic outsider free-form injection surface.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata