researching-a-topic

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 2 "Source Collection & Crawling" and Tools Available explicitly require using webfetch to gather content from public websites and gh_grep to search GitHub, so the agent ingests untrusted, user‑generated third‑party content and uses it to drive research decisions.