vercel-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs the agent to fetch and read content from user deployments and logs (e.g., "vercel curl /... --deployment $PREVIEW_URL" and "vercel logs " in references/monitoring-and-debugging.md and deployment.md), which are untrusted, user-controlled web content that the agent is expected to interpret and that could materially influence subsequent commands.