skill-lifecycle-manager

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow runs scripts/lifecycle_report.py, which reads skills/*/SKILL.md and evals/evals.json from the repository filesystem; these are outsider-authored free text if the repo contains skills not authored by the operating user (e.g., other maintainers’ skill docs), and that text is ingested via skill_md.read_text() into the LLM context through the tool’s printed JSON/text output.