ra-qm-skills
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data exfiltration mechanisms were detected across the 81 files.
- [COMMAND_EXECUTION]: The collection includes over 20 Python scripts designed for regulatory tracking, risk assessment, and compliance auditing. A detailed review confirms these scripts use only the Python standard library (e.g.,
argparse,json,csv,datetime,re) and perform benign operations such as calculating risk scores, generating markdown reports, and managing local document versioning. - [DATA_EXFILTRATION]: No network libraries (such as
requestsorurllib) are utilized in the automation tools. The scripts perform local file system analysis only, and results are presented to the user/agent without external transmission. - [PROMPT_INJECTION]: The instructions in the
SKILL.mdfiles are appropriately scoped to establish professional personas (e.g., Regulatory Affairs Manager, CAPA Officer) and provide valid workflow guidance without attempting to bypass agent safety filters or override core instructions.
Audit Metadata