vercel-cli-with-tokens

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly fetches and parses external, user-generated content (e.g., "git clone ", "vercel ls --format json", "vercel inspect ", and "vercel logs " in SKILL.md), so the agent would ingest untrusted repository, deployment, and log data and use it to determine next actions.