gmgn-holder-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a Python script (analyze.py) to execute the gmgn-cli tool via subprocess.run. This is used to fetch and analyze blockchain data. The implementation uses argument lists rather than shell strings, which is a secure practice that prevents shell injection.
- [EXTERNAL_DOWNLOADS]: The skill instructions advise the user to install the gmgn-cli package globally via NPM. As the package belongs to the skill's authoring vendor (GMGNAI), it is considered an intended vendor resource for the skill's operation.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted data from an external API (via gmgn-cli) and is instructed to output the results verbatim to the agent. Maliciously crafted data in the blockchain or API response could theoretically attempt to influence the agent's behavior.
- Ingestion points: Data enters the script through the stdout of gmgn-cli calls in analyze.py.
- Boundary markers: The skill lacks explicit delimiters or warnings to the agent to ignore instructions embedded within the tool's output.
- Capability inventory: The script has the capability to execute the gmgn-cli tool and print its output to the agent's context.
- Sanitization: No sanitization or filtering is performed on the data retrieved from the external source before it is presented to the agent.
Audit Metadata