agnt-cli-builder
Warn
Audited by Snyk on Oct 25, 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). The skill instructs the agent to clone and read GitHub repositories (
gh repo clone,gh pr view,docs/blueprint.md), which can contain outsider-authored pull requests, issues, and code content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata