exa-websets-monitor
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: 0.80). The skill creates and runs periodic searches and webset updates (e.g., via commands like "exa-ai webset-create --search '{"query":"..."}'" and "exa-ai monitor-create" with behavior-type search/refresh), which ingest and refresh content from open web search results and third-party pages, exposing the agent to untrusted user-generated web content.
Audit Metadata