grok-search

Warn

Audited by Snyk on Mar 24, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The grok-search skill explicitly instructs Grok to use server-side web_search and x_search tools via the xAI Responses API (see scripts/grok_search.mjs and SKILL.md) to fetch public web pages and X/Twitter content, parses that untrusted/user-generated content (snippets/citations) as part of its workflow, and uses it to generate structured outputs—exposing the agent to indirect prompt injection from third‑party content.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 12:27 AM
Issues
1