tools-integration-ci

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

• Third-party content exposure detected (high risk: 0.75). High: the required workflow for checks status / checks wait auto-downloads failing-job logs from the CI provider (outsider-authored text from GitHub/GitLab), filters them, and returns the resulting log content/lines in the TOON output that is then available to the agent’s LLM context.