dojo-richard-rumelt
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 agent adheres to the provided persona and frameworks. These are standard techniques for maintaining persona fidelity and do not attempt to bypass system safety constraints or extract system prompts.
- [DATA_EXFILTRATION]: No network operations, credential harvesting, or access to sensitive local file paths were detected. The skill only references its own local Markdown files.
- [REMOTE_CODE_EXECUTION]: There is no executable code (Python, JavaScript, or Shell) included in the skill. It relies purely on text-based prompting and local file retrieval.
- [OBFUSCATION]: A thorough scan for Base64 encoding, zero-width characters, homoglyphs, and hidden text patterns revealed no obfuscated content or hidden URLs.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user questions, it has a very narrow capability surface. It does not use external tools or APIs that could be manipulated to execute commands or exfiltrate data. Its scope is limited to text generation based on provided local knowledge files.
Audit Metadata