gmgn-wallet-score
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 wallet-scoring tool, but its IPv6 troubleshooting block tells the agent to run network diagnostics and an external probe, then tells the user to disable IPv6 on their network interface, a system change beyond what the scoring task needs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow pulls GMGN wallet data (stats, activity, created-tokens, token security) for a user-supplied address, and the script prints the wallet's self-settable
twitter_name/name/enslabel into the report, so outsider-authored text reaches the LLM only after the user picks a wallet to score.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata