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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata