CI Orchestration
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill reads and interprets external CI and PR content (e.g., via
gh pr view --json statusCheckRollup,gh pr checks,gh run view --log-failed) and extracts preview URLs from CI output (Vercel/Netlify), which are untrusted, user-generated third-party sources that the agent consumes at runtime.
Audit Metadata