ben-heath
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The file contains instructions for persona maintenance and character consistency. These do not attempt to bypass the AI's core safety filters or extract system prompts for malicious purposes.
- [Data Exposure & Exfiltration] (SAFE): No evidence of hardcoded credentials, sensitive file path access, or unauthorized network communication was found.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include or reference external scripts, packages, or executable commands.
- [Obfuscation] (SAFE): The text is clear and does not use encoding, zero-width characters, or homoglyphs to hide malicious intent.
- [Indirect Prompt Injection] (SAFE): While the skill processes user queries to call retrieval tools, these tools are limited to domain-specific knowledge retrieval and do not have access to sensitive system functions or data writing capabilities.
Audit Metadata