research-grants
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of Markdown documentation and templates. No executable scripts (.py, .js, .sh) or configuration files that trigger code execution were found.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill contains links to official government domains (nsf.gov, nih.gov, osti.gov, darpa.mil). These are high-trust sources used for legitimate reference purposes.
- [DATA_EXFILTRATION] (SAFE): No network-enabled tools, hardcoded credentials, or access patterns for sensitive local files (e.g., SSH keys, environment variables) were detected.
- [PROMPT_INJECTION] (SAFE): The instructions are focused on providing templates and guidance. There are no patterns indicative of system prompt overrides, role-play jailbreaks, or instructions to ignore safety filters.
Audit Metadata