gmgn-portfolio
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 wallet-analysis CLI guide, but its IPv6 troubleshooting block has the agent run network-interface inspection and an external IP-echo request, then tell the user to disable IPv6, an unexpected network change beyond the task's needs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow reads GMGN portfolio data for a user-supplied wallet, and token names and symbols in holdings and created-tokens responses are free text set by arbitrary token deployers, who can also airdrop tokens into a target wallet, so an outsider can get text into the LLM's context without the agent selecting that item.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata