autonomous-loops
Warn
Audited by Snyk on Jun 24, 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’s runtime workflow (e.g., “Continuous Claude PR Loop” / “Ralphinho” patterns) ingests free-form text from CI logs and PR/check failure details via
gh run view/gh pr checksand then feeds that text back into subsequentclaude -pprompts, and those log/check contents are outsider-authored (GitHub Actions/CI output and PR check systems) rather than authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata