deep-research
Warn
Audited by Snyk on May 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly requires live discovery and fetching of public web sources (see "Core Rules" and "Workflow — Step 3: Discover sources" which mandate using websearch_cited, Brave Search, webfetch, and Bing and then extracting page claims), so the agent will ingest untrusted public third‑party content that can materially influence decisions and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata