gmgn-market
Fail
Audited by Snyk on Nov 14, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate GMGN market-data tool, but its IPv6 section tells the agent to probe the network with a third-party request and to instruct the user to disable IPv6 on their interface after any 401/403, an unexpected system change the advertised task does not need.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required
market trenches,market trending,market signal, andmarket hot-searchesworkflows read token name, symbol, and social-link fields from a feed that any outsider can populate by launching a token, so the agent ingests attacker-controlled text without first selecting a specific item.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata