ci

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests CI logs from third‑party CI systems (e.g., "gh run view --log" in references/analyzing-failures.md) and also passes the collected error_log into a subagent prompt (SKILL.md's Task tool invocation), meaning untrusted, user-generated CI/build logs are read and can directly influence analysis and automated fix actions.