gourmet-research
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for food research and data management. All repository operations and research tasks align with the stated purpose without introducing security risks.
- [COMMAND_EXECUTION]: The script
scripts/verify_city.shis used to verify the completion of research tasks by searching for placeholders like 'TODO' or 'inbox' status. It uses safe shell scripting practices, including proper variable quoting and safe flag usage for search utilities (grep,rg), preventing command injection risks. - [DATA_EXFILTRATION]: The skill's workflow involves retrieving information from public restaurant review platforms and mapping services. No patterns were found indicating the exfiltration of sensitive local data or unauthorized network operations.
- [PROMPT_INJECTION]: Instructions in the skill focus on maintaining auditability and consistent scoring. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.
Audit Metadata