exa-websets-search
Warn
Audited by Snyk on Feb 16, 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 performs open web searches and ingests public content (e.g., via exa-ai webset-create and exa-ai webset-search-create which run arbitrary queries and pull items/articles/URLs from the web) and then has the agent read and enrich those items, so it clearly consumes untrusted third‑party content.
Audit Metadata