people-research

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires using web_search_advanced_exa to fetch and process public LinkedIn profiles, personal sites, news and other web results (untrusted, user-generated third‑party content) in spawned Task agents, so the agent will read and act on arbitrary external webpages that could contain injected instructions.