grok-ai

Warn

Audited by Snyk on Feb 28, 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.md explicitly automates visiting x.com/i/grok and scraping Grok AI responses and tweet pages (e.g., "Any tweet") via XActions.scrapeResponse(), so the agent reads untrusted, user-generated third-party content (tweets and Grok outputs) that can influence subsequent automated actions like thread composition.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:53 AM