deep-research-pro

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 workflow and README explicitly run web_search (DuckDuckGo) and web_fetch on open URLs (Step 3 and Step 4) to read full third‑party web pages and synthesize them into reports, meaning untrusted public content is ingested and used to drive agent decisions.