NYC

groksearch

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). The skill calls the xAI API (XAI_RESPONSES_URL) with tools "web_search" and "x_search" (see build_tools in scripts/groksearch.py), causing it to ingest web pages and X posts—untrusted, user-generated third‑party content—which the script then reads/prints as Grok's summarized output and citations.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:21 AM