super-agent
Fail
Audited by Snyk on Nov 18, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a documented orchestration workflow with no concealment or pretext, but it lets the super agent rule on merge-gate holds and close parent issues without asking the owner, which is a self-granted action the user might not expect.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow reads outsider-authored GitHub issue text (titles and comments) without the agent selecting an item:
launch.shreads each ticket's issue,intake.shlists every openready-for-agentissue of the active repos, andclaim.shreads the issue's comments.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata