deep-research
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly requires the main agent to run 3 Exa searches via the
exa-toolsdependency (described as "Web search and code context queries") and to extract facets and sources from those web search results, meaning it ingests and interprets open/public third‑party content as part of its workflow.
Audit Metadata