actions-debugging

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md describes runtime tool calls (e.g., github-mcp-server-get_job_logs with return_content: true) that fetch and ingest GitHub Actions job log text authored by other parties (CI steps/third-party actions), which can include free-form log content and thus indirect prompt-injection payloads.