tech-blog

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

• Third-party content exposure detected (high risk: 0.80). The skill's Research Strategy/Doc-Driven Research sections explicitly instruct the agent to "find authoritative sources (official docs → vendor blogs → community)" and to use reference-style links (https://...), which requires fetching and reading public/vendor/community web content and user-generated material that is untrusted.