agent-search

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow ingests outsider-authored free text via the required quick/verify/chinese path calling free_search (search result snippets) and the extract path calling free_extract on user-supplied or selected public URLs, so an outsider can submit content that the workflow reads.