watch-ci

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries the public GitHub REST API (api.github.com) in SKILL.md to fetch workflow runs, job steps, and failure logs for codervisor/lean-spec, and those user-generated CI logs/step names are parsed and used to decide polling/reporting, creating a clear path for untrusted third-party content to influence agent behavior.