xai

Warn

Audited by Snyk on Mar 7, 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). scripts/search-x.js uses the x_search tool via the xAI Responses API to fetch real X/Twitter posts (public, user-generated content) and the skill parses and incorporates those tweets and citations into its workflow/output, allowing third-party text to influence model responses and behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 07:55 AM