summon
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown documentation and reference files. No executable scripts (Python, JavaScript, shell) or binary files are present in the package.
- [NO_CODE]: There are no commands or instructions that trigger external network calls, file system modifications, or process execution. The skill operates entirely within the context of text-based persona adoption.
- [SAFE]: Analysis of the 41 expert persona files (e.g., Steve Jobs, DHH, Julia Evans) found no evidence of prompt injection, hidden instructions, or malicious obfuscation. The files contain factual biographies, quotes, and technical opinions used to guide the agent's reasoning.
- [SAFE]: The 'Extrapolation Protocol' and role-playing instructions are professional in nature and do not attempt to bypass core AI safety guardrails or request the removal of constraints.
Audit Metadata