dojo-peter-thiel
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown files providing business strategy frameworks and persona instructions. There are no executable scripts (.sh, .py, .js) or configurations that interact with the host system or network.
- [NO_CODE]: No code was found in the analyzed files. The skill functions as a retrieval-augmented persona, where the agent is instructed to read local Markdown documents to inform its responses.
- [PROMPT_INJECTION]: The instructions provided are focused on maintaining persona consistency (e.g., 'Never blend their voices', 'answer in Thiel's voice'). There are no malicious override patterns, attempts to bypass safety filters, or requests to reveal system prompts.
Audit Metadata