grok-search

Warn

Audited by Snyk on Mar 12, 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 explicitly instructs the assistant to "Use live web search/browsing" and to prioritize fresh social/community sources (see MODE_SYSTEM_PROMPTS in scripts/grok_search.py and the SKILL.md which recommends --mode news/--mode social for X/Twitter and community chatter), so it ingests and returns untrusted public web/social content that can materially influence outputs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 02:53 AM
Issues
1