exa-find-similar
Warn
Audited by Snyk on Mar 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: 0.90). The SKILL.md explicitly instructs running exa-ai find-similar against arbitrary public URLs (e.g., https://techcrunch.com, https://arxiv.org, https://anthropic.com), meaning the agent fetches and interprets untrusted third-party web content which can materially influence results and follow-up actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata