tao-train-mask-auto-label
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected in instructions or scripts.
- [CREDENTIALS_UNSAFE]: The
encryption_keyparameter in the schemas defaults to an empty string. While this is not a leak of a private secret, it represents a default configuration that users should be aware of when handling encrypted models as noted in the skill's own benchmark report. - [DATA_EXFILTRATION]: Weights & Biases (WandB) integration is enabled by default (
enable: true) in the action schemas. This is a standard machine learning experiment-tracking feature but results in training metadata being sent to the WandB platform unless disabled by the user.
Audit Metadata