gmgn-portfolio
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'gmgn-cli' package globally via npm. This package is the primary tool used by the skill and is a vendor resource associated with the skill's functionality.
- [COMMAND_EXECUTION]: The skill uses various shell commands for setup and data retrieval. This includes using 'openssl' to generate a key pair in the system's temporary directory, as well as filesystem operations ('mkdir', 'echo', 'chmod') to create and secure a configuration file at '~/.config/gmgn/.env'.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from blockchain records (such as wallet tags, names, and ENS domains).
- Ingestion points: Data returned from 'gmgn-cli' regarding wallet identity and token metadata (SKILL.md).
- Boundary markers: None identified in the prompt instructions to delineate external data from agent instructions.
- Capability inventory: The agent can execute 'gmgn-cli' commands based on the data processed.
- Sanitization: There is no explicit instruction to sanitize or validate the content of the external strings before presentation.
Audit Metadata