om-auto-continue-pr-loop
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). At runtime the skill reads outsider-authored free text from the PR body via the tracker’s
get-prcall (fields includebody), and then uses that untrusted content to locate the run folder and resume progress (tracking plan/run folder lines), plus it later parsesHANDOFF.md/PLAN.mdfrom the run directory as the session context for execution.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata