xai-grok

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: 1.00). This skill explicitly performs real-time X (Twitter) searches and web browsing (see SKILL.md and src/grok.py where x_search() and web_search() are added as tools), so the agent ingests untrusted, user-generated public web/social media content and is exposed to indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:26 AM