grok-search
Warn
Audited by Snyk on May 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly uses web_fetch ("fetch and extract full page content") and web_map ("crawl site structure from a root URL") as required execution tools (see SKILL.md Execution tools and references/grok-search.md), so the agent ingests arbitrary public web pages that could contain untrusted, user-generated instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata