deployments-cicd

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read and act on deployment-specific, user-provided content (e.g., "vercel inspect ", "vercel logs ", and "Visit the preview URL to verify" plus the "Deploy Summary Format" which pulls error summaries from logs), which are untrusted third-party deployment pages/logs that the agent must interpret and which can directly influence actions like promote/rollback.