vercel-deploy
Warn
Audited by Snyk on Apr 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md) explicitly instructs fetching and inspecting deployed public URLs (e.g., "vercel curl /api/health --deployment ",
vercel inspect <deployment-url>, and reading deployment outputs from the claimable preview URL produced by scripts/deploy.sh), which causes the agent to ingest arbitrary public/third-party app content that can influence promote/rollback decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata