dojo-wes-kao
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong instructional language such as 'REQUIRED READ' and 'MUST read' to ensure the AI agent adheres to the expert persona. These directives are intended for persona consistency and do not attempt to bypass underlying system safety guidelines or extract system prompts.
- [DATA_EXFILTRATION]: No network operations, sensitive file path access (e.g., .ssh, .aws), or hardcoded credentials were found in any of the skill's files. The skill operates entirely on provided markdown content.
- [REMOTE_CODE_EXECUTION]: There are no external dependencies, package installation commands (npm, pip), or remote script downloads identified in the provided materials.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic execution patterns were detected in the instructions or topic files.
- [NO_CODE]: The skill is composed entirely of Markdown documentation (
SKILL.md,persona.md, and various topic files). It teaches the agent how to communicate using specific frameworks without requiring executable code.
Audit Metadata