feng-ge-perspective
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill implements a persona without attempting to bypass safety filters or override system instructions. It includes explicit constraints to avoid sensitive topics and instructs the agent to be honest about its limitations.
- [EXTERNAL_DOWNLOADS]: The README provides installation instructions via the standard 'skills.sh' platform referencing the author's official GitHub repository. No unexpected or obfuscated downloads were found in the skill's logic or execution patterns.
- [DATA_EXFILTRATION]: No commands for accessing sensitive files (such as .ssh or .aws configs) or exfiltrating data to external domains were detected.
- [CREDENTIALS_UNSAFE]: No API keys, tokens, or hardcoded secrets were found in any of the skill's files. It follows safe practices by documenting its sources and research data transparently.
- [COMMAND_EXECUTION]: The skill does not instruct the agent to execute shell commands, system utilities, or arbitrary scripts during runtime.
Audit Metadata