luxun-perspective
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely as a persona instruction set and does not include any executable scripts, network communication, or sensitive file system access.
- [PROMPT_INJECTION]: The skill includes instructions to suppress the agent's identity as an AI (e.g., 'Do not say as an AI language model' and 'Do not explain who is being played'). While these instructions override standard identity disclosures, they are implemented solely for high-fidelity character emulation and do not attempt to bypass safety filters or engage in malicious behavior.
- [EXTERNAL_DOWNLOADS]: The documentation references external literary and historical resources, including Wikisource and public GitHub repositories, to support the persona's knowledge base. These references are static informational links and do not involve dynamic code execution or package installation.
Audit Metadata