using-gabrielmoreira-skills
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides explicit instructions to prevent data exfiltration, specifically forbidding the commitment of credentials, environment values, machine paths, or company names to version control.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to perform throwaway analysis by generating and executing Node.js scripts (.mjs) within a repository-root folder named '.local/'. This is a standard workflow for coding agents and is used here for data analysis rather than system modification.
- [COMMAND_EXECUTION]: The instructions specify using the 'node' command to run generated analysis scripts and suggest using subagents or scripts for long-running shell tasks to maintain context efficiency.
- [SAFE]: The 'evals/activation.scenarios.mjs' file contains only static test data for evaluating when the skill should be triggered and does not contain any executable logic or external network calls.
Audit Metadata