exa-search

Warn

Audited by Snyk on Aug 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a runtime workflow that uses Exa’s POST https://api.exa.ai/search endpoint to retrieve and optionally extract page text/highlights/summaries from search results, which can include outsider-authored web content when the user-supplied query/includeDomains directs retrieval.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 04:13 AM
Issues
1
Security Audit — snyk — exa-search