grok-prompting
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill is composed entirely of Markdown documentation files within the root and references directory. No executable code, shell scripts, or binaries were found.
- [NO_CODE] (SAFE): There are no software dependencies, package manifests (such as package.json or requirements.txt), or external libraries referenced for installation or runtime use.
- [PROMPT_INJECTION] (SAFE): While the content includes prompt templates and techniques like 'Roast Mode' or 'Devil's Advocate', these are provided as educational examples for interacting with an external LLM and do not contain instructions to override the host agent's safety protocols.
- [EXTERNAL_DOWNLOADS] (SAFE): No remote URLs, script downloads, or external data fetching patterns were identified in the files.
Audit Metadata