gmgn-swap
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to ensure the
gmgn-cliutility is installed or updated from the NPM registry. This is a standard software distribution method for the vendor's tools and does not involve untrusted third-party scripts. - [COMMAND_EXECUTION]: The skill operates primarily through shell command execution using the
gmgn-clitool to perform blockchain transactions. It also uses standard system utilities likeifconfigorip addrto diagnose network configuration issues, specifically to detect unsupported IPv6 environments. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data returned from blockchain queries and API calls via the CLI. It includes defensive instructions to validate address formats, quote shell arguments, and ignore any instruction-like text embedded in API response fields to mitigate potential injection risks. It documents a clear ingestion point for untrusted data and provides specific sanitization guidelines.
- [SAFE]: The skill implements a mandatory security verification step using
gmgn-cli token securitythat checks for known malicious patterns such as 'honeypots' and high 'rug ratios' before executing transactions, which serves as a significant protective measure for users.
Audit Metadata