partner-nvidia
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, product information, and persona guidelines. No executable scripts or system commands are present.
- [DATA_EXPOSURE]: The file references several internal documentation paths (e.g.,
.frankx/private/partnerships/nvidia-brief.md) for context, but it does not include instructions to read, parse, or exfiltrate the contents of these files. - [PROMPT_INJECTION]: The 'Voice rules' section provides legitimate constraints for the AI agent to maintain a specific professional persona and ensure factual accuracy. These instructions do not attempt to bypass safety filters or override core agent behavior.
- [REMOTE_CODE_EXECUTION]: There are no remote code downloads, package installations, or script executions identified in the file.
Audit Metadata