manual-testing
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Several scripts within the skill, such as
batch_convert_templates.pyandconvert_output_formats.py, usesubprocess.callto execute local Python conversion logic. These operations are performed securely by passing arguments as lists and specifically calling thesys.executable, which limits execution to the local environment and the skill's own scripts. - [SAFE]: No network-based operations (like
curl,wget, orrequests) were detected, precluding data exfiltration or external payload downloads. - [SAFE]: The primary prompt in
prompts/manual-testing.mdprovides standard QA guidance and does not attempt to bypass safety filters or override agent instructions. - [SAFE]: File access is restricted to reading templates and writing conversion results to a local artifacts directory, with no access to sensitive system paths or credentials.
Audit Metadata