ml-engineer
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and capabilities are consistent with its stated purpose of assisting in ML engineering tasks. No patterns of prompt injection, data exfiltration, or persistence were detected.
- [SAFE]: The code snippets in the implementation playbook provide standard industry examples for model serving (FastAPI), monitoring (Evidently), and feature engineering (Feast). While the use of
joblib.loadinvolves deserialization, it is presented as a standard functional pattern for loading local models and does not constitute a malicious execution vector in this context.
Audit Metadata