amd
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown-based instructions and technical documentation. No executable scripts, binaries, or active code files are included in the package.
- [EXTERNAL_DOWNLOADS]: The documentation includes installation instructions for Claude Code that reference a configuration file hosted on GitHub (raw.githubusercontent.com). This is a well-known service used for distributing skill definitions and does not involve automated remote code execution.
- [PROMPT_INJECTION]: The system prompts are designed to establish a technical persona (AMD Senior Fellow). There are no instructions aimed at overriding safety guidelines, bypassing agent constraints, or extracting system prompts.
- [COMMAND_EXECUTION]: While the skill contains shell commands for installation (appending to a local configuration file), these are provided as documentation for the user and are not executed autonomously by the skill itself.
Audit Metadata