research-synthesize

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly ingests and reads scraped, potentially adversarial third‑party evidence files (collect/evidence/.md and collect/evidence/gap-fill/.md) as required inputs and uses them to drive synthesis, citation audits, gap‑fill triggers, and spawning the research-collector, so external web content can materially influence agent decisions and tool use.