vercel-common-errors

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and interpret deployment and build logs from Vercel (e.g., via "vercel logs", "vercel inspect ", and curl to "https://api.vercel.com/..."), which are third-party, user-generated/untrusted content the agent must read and that can directly influence debugging decisions and follow-up actions.