grok-search

Warn

Audited by Snyk on Apr 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill performs real-time web research and explicitly enables a web search tool—see SKILL.md/README describing "real-time web search" and scripts/grok_search.py where _DEFAULT_SYSTEM_PROMPT tells the model to "Use live web search/browsing" and _request_responses includes "tools": [{"type": "web_search"}]—so it ingests untrusted public web content that can materially influence the assistant's responses.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 18, 2026, 02:48 AM
Issues
1