atai-manual-generation-agent
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
run_mga_agent.pyintended for local execution by the user to interact with the Archetype AI API. The script uses only Python standard libraries and performs legitimate operations such as file uploads and HTTP requests to author-owned infrastructure (api.u1.archetypeai.app). - [DATA_EXPOSURE]: The provided helper script manages credentials via environment variables and
.envfiles. It includes explicit warnings and implementation details (unique file naming) to prevent accidental data overwrites or exposure within an organization's shared API namespace. - [DYNAMIC_EXECUTION]: The test file
tests/test_references.pyusesimportlibto dynamically load the local script for testing purposes. This is a standard development practice for testing standalone scripts and does not process untrusted external input. - [SAFE]: All identified network communications and dependencies are restricted to the author's official domains and the Python standard library, posing no risk of unauthorized data exfiltration or third-party dependency compromise.
Audit Metadata