logs

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

• Third-party content exposure detected (high risk: 0.70). The required workflow uses the Vercel CLI to fetch and display log text from a user-supplied <deployment-url> at runtime; those logs are outsider-authored content (from Vercel deployments/other actors) that can include arbitrary free-form messages, which the agent’s LLM ingests via the CLI output.