munger-perspective
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses role-playing instructions to adopt the Charlie Munger persona. It includes a clear '退出角色' (exit character) mechanism and standard constraints to maintain style without attempting to bypass safety filters.
- [COMMAND_EXECUTION]: No shell commands, script executions, or dynamic context injections (!command) were found within the skill instructions or referenced files.
- [DATA_EXFILTRATION]: There is no evidence of sensitive file access or network operations targeting unauthorized domains. Use of web search tools is restricted to gathering public business and financial information.
- [EXTERNAL_DOWNLOADS]: The skill is installed using the platform's standard 'npx skills add' command and references other skills from the same author's (xmg2024) ecosystem, maintaining vendor consistency.
- [SAFE]: The skill represents a legitimate use of AI for persona-based decision analysis. While it ingests external data from web searches (Indirect Prompt Injection surface), this is consistent with its primary purpose and carries low risk due to the lack of dangerous capabilities.
Audit Metadata