scrape

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

• Third-party content exposure detected (medium risk: 0.30). Skill.md Step 1b/1c ingests outsider-authored free text at runtime by running WebSearch/WebFetch for search index results and then fetching full job posting text from the posting URLs (Step 2: “From WebSearch results: Use WebFetch on the posting URL and extract…”), which an outsider can influence by publishing poison job postings or search-indexed content.