babysit
Warn
Audited by Snyk on Jul 17, 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). This skill’s required workflow involves reading an open pull request’s unresolved review comment bodies and CI/job logs at runtime (outsider-authored PR/discussion content), which would be ingested into the agent’s LLM context via the PR/comment-fetching steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata