using-medusa-cloud

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

• Third-party content exposure detected (high risk: 0.90). The skill’s workflow (SKILL.md and reference/debugging-deployments.md) explicitly instructs the agent to run commands like "mcloud deployments build-logs" and "mcloud logs" to ingest build/runtime logs and deployment metadata from Medusa Cloud (user-generated/untrusted content) and then make decisions such as redeploying or triggering builds based on that content, which could allow indirect prompt-injection via log or deployment output.