dan-koe
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 and instructions. It does not include scripts, executables, or any logic that interacts with the host system's shell or network.
- Prompt Injection (SAFE): While the skill contains instructions to adopt a specific persona ('Dan Koe') and includes templates for prompt engineering (e.g., in the
ai-usagesub-skill), these are intended as educational content for the user. There are no directives aimed at bypassing the underlying agent's safety filters or extracting its system prompt. - Data Exposure & Exfiltration (SAFE): No file system access or network transmission capabilities are present in any of the skill files.
- Unverifiable Dependencies (SAFE): The skill does not reference or install any external Python or Node.js packages.
- Indirect Prompt Injection (LOW): The skill is designed to process user questions to provide advice. While this is an ingestion point for untrusted data, the skill lacks any dangerous capabilities (like file writing or command execution) that could be exploited via an injection attack.
Audit Metadata