analyze-ci-failures

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 2: "Fetch CI Failure Details") explicitly instructs the agent to fetch and read CircleCI build/test logs from a provided CircleCI URL (public API), which are third-party, user-generated/untrusted logs that the agent will interpret and use to drive analysis and actions, exposing it to potential indirect prompt injection.