xai-search
Warn
Audited by Snyk on Mar 1, 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.md explicitly invokes Grok's web_search and x_search tools to query "the web" and "X/Twitter" (public social media and web pages), which are untrusted, user-generated third‑party sources that the agent will read and use agentically to drive its responses, enabling potential indirect prompt injection.
Audit Metadata