exa-search
Warn
Audited by Snyk on Feb 15, 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 uses Exa methods like search_and_contents and get_contents (references/contents.md and sdk-patterns.md) to fetch full page text, highlights, and summaries from arbitrary public URLs and categories (including user-generated sources like "tweet", Medium, GitHub, dev.to), so the agent will read untrusted third‑party content.
Audit Metadata