gmgn-dev-score
Warn
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
dev_score.pyusessubprocess.runto execute thegmgn-clibinary. While this is the intended functionality of the skill, it passes user-supplied arguments (chain,dev_address) directly to the shell command. Although some sanitization is implemented via thesafe()function for display, the initial command execution relies on the integrity of thegmgn-clitool and shell-level handling. - [EXTERNAL_DOWNLOADS]: The skill performs multiple automated network requests to
gmgn.aiAPIs via thegmgn-clitool to fetch wallet history, token info, and trading stats. It also fetches data fromipv6.icanhazip.comto check the user's network configuration. - [DYNAMIC_EXECUTION]: The
SKILL.mdfile contains instructions for the agent to execute shell commands (python3 ~/.claude/skills/gmgn-dev-score/dev_score.py ...) and use the output to generate a report. It also includes conditional logic that dictates agent behavior based on the command's exit code or specific JSON outputs (e.g.,scored: false). - [INDIRECT_PROMPT_INJECTION]: The skill processes data from a highly adversarial environment (blockchain token metadata, symbols, and wallet addresses). The developer has acknowledged this by implementing a
safe()function to strip ANSI escapes and non-printable characters, but the risk remains that malicious data from the API could influence the agent's report generation or logic.
Audit Metadata