shaman-buffett
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of markdown-based prompt instructions and metadata. It contains no executable scripts, shell commands, or binary files.
- [PROMPT_INJECTION]: The skill establishes an authoritative 'shaman' persona designed to judge investment logic. While the persona uses assertive and sometimes aggressive roleplay language (e.g., 'wealth shaming'), it does not include instructions intended to bypass AI safety filters, extract system prompts, or override core agent constraints.
- [DATA_EXFILTRATION]: No network communication patterns (e.g., curl, wget) or sensitive file system access patterns were identified.
- [REMOTE_CODE_EXECUTION]: The skill does not define any external dependencies or remote script loading mechanisms.
Audit Metadata