run-with-it
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s runtime path assembles each Sub-Coordinator context by re-fetching GitHub issue body and comments via
gh issue view ... --json ... body,comments, and that outsider-authored free text (issue/PR discussion content) is then written into the context file consumed by the agent LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata