design-guide
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely informational, providing guidance on how to use other design skills within the agent environment. It does not include any scripts, command execution logic, or external network requests.
- [PROMPT_INJECTION]: The skill contains explicit defensive instructions to treat user input as data only and not as instructions, which is a recommended security practice for mitigating prompt injection.
- [DATA_EXFILTRATION]: There is no evidence of data exfiltration or unauthorized access to local files. No sensitive file paths, environment variables, or network utilities are referenced.
- [REMOTE_CODE_EXECUTION]: No remote code patterns, package dependencies, or dynamic code execution methods were found in the analyzed files.
Audit Metadata