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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:39 AM