fetch-ci-build

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and parses CI logs from external CI providers (e.g., Buildkite raw_log_url in scripts/fetch_buildkite_failures.py, CircleCI step output URLs in scripts/fetch_circleci_failures.py, and GitHub Actions logs via gh run view), which are untrusted/user-generated third-party content that the agent reads as part of its workflow.