deep-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires using built-in WebSearch/WebFetch via multiple "ResearchScout" agents to fetch and ingest public web pages (and the evals even reference user-review sites like G2/Capterra), so untrusted, user-generated third-party content is read and synthesized into recommendations and decisions.