ansible-validator

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md "Custom Module and Collection Documentation Lookup" step explicitly calls Context7 and falls back to web.search_query to fetch and parse public docs (docs.ansible.com, galaxy.ansible.com, GitHub, arbitrary web search results) as part of its workflow, so untrusted third‑party content is ingested and can influence guidance and actions.