ai-assisted-testing

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Multiple Python scripts in the scripts/ directory, including batch_convert_templates.py and various convert_to_*.py wrappers, use subprocess.call to invoke a central conversion engine (convert_formats.py). These calls are used to process local files and documentation, using controlled arguments and absolute paths. There is no evidence of shell injection or execution of untrusted commands.- [SAFE]: The skill does not perform any network operations, data exfiltration, or access sensitive system paths. All file processing (parsing ZIP, XML, and JSON) is handled using standard Python libraries on local documentation files.- [SAFE]: The prompt instructions in prompts/ai-assisted-testing.md provide a structured role for a QA expert. They do not contain any instructions to bypass agent constraints, reveal system prompts, or ignore safety guidelines.- [SAFE]: No obfuscation, hidden URLs, or dynamic code generation from untrusted sources were detected in any of the skill's files or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 09:00 AM