exa-tools

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). This skill issues web searches and GitHub code/context searches (see the "search" and "code" commands and description "searching the web" and "GitHub") that ingest public, user-generated content which the agent reads as part of its workflow, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:13 PM