exa-unified-research
Warn
Audited by Snyk on Apr 12, 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 explicitly requires using Exa search/fetch tools (web_search_exa, web_search_advanced_exa, and web_fetch_exa) to discover and read public websites, blogs, research papers, and social media (see SKILL.md and references/social-discussion.md which even instruct includeDomains ["x.com","twitter.com"]) and to synthesize that content into decisions, so untrusted third‑party content can directly influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata