deepvista-recipe-research-to-recipe
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill utilizes the vendor's own 'deepvista' CLI tools to search for and process data within its intended ecosystem.
- [COMMAND_EXECUTION]: The skill uses local CLI commands for research and recipe execution. These are consistent with the skill's stated purpose and include explicit instructions for the agent to seek user confirmation before execution.
- [PROMPT_INJECTION]: While the skill ingests data from a knowledge base that could theoretically contain indirect prompt injections, the risk is mitigated by the instruction to confirm with the user before performing significant actions.
Audit Metadata