ci-report

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

• Third-party content exposure detected (medium risk: 0.30). At runtime the skill reads outsider-authored free text from GitHub/GitLab job failure logs (e.g., “github.failures” extracted from failed GitHub Actions logs and GitLab job logs fetched by get_job_log and split into logText for error snippets), which can contain arbitrary content submitted by repo authors.