agent-task-risk-classifier
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs risk classification based on user-provided task facts using a local Python script, following a clear security methodology (least privilege).
- [SAFE]: The script
scripts/classify-task.pyuses standard library modules (json,sys,pathlib) to process JSON input and does not perform any dangerous operations such as network requests, arbitrary command execution, or privilege escalation. - [SAFE]: The logic for determining risk profiles is transparently defined in
references/profile-rules.mdand correctly implemented in the classification script, aiming to reduce the ambient authority of the agent. - [SAFE]: No sensitive data exposure, prompt injection patterns, or obfuscation techniques were detected in the skill files or metadata.
Audit Metadata