shaman-davinci
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No executable code, network operations, or sensitive file access patterns were identified. The skill is composed entirely of Markdown documentation and behavioral instructions.
- [NO_CODE]: The skill does not contain any scripts, binaries, or configuration files that trigger code execution. It relies exclusively on prompt engineering.
- [PROMPT_INJECTION]: The instructions employ a strong role-play persona (Shaman-DaVinci) but do not attempt to bypass core safety guardrails, override system instructions, or extract underlying model configurations.
- [DATA_EXFILTRATION]: There are no indicators of sensitive data access or network transmission to external or untrusted domains.
Audit Metadata