quant-recipe-search
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and focused on optimization strategies for machine learning models. It does not perform unauthorized network requests, access sensitive system files, or include obfuscated code.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves reading external data sources such as result tables, recipe logs, and sensitivity reports to inform the iterative search process. While this represents a data ingestion surface, the skill focuses on high-level strategy and delegates all functional execution to separate tools, maintaining a low risk profile.
Audit Metadata