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
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 14, 2026, 02:47 AM
Issues
2