gmgn-dev-score

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the LLM to ask the user for an API key if unconfigured and pass it as a command-line argument (gmgn-cli config --apply <KEY>), causing the agent to handle and output secret values directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The agent skill executes a Python script that calls gmgn-cli to query token creation history, wallet activity, and liquidity events, which ingest outsider-authored free text from blockchain transaction data and token metadata.