@6522/jacob-ham-mode
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions intended to guide the AI's persona and conversational style. No security vulnerabilities were identified during the analysis.
- [NO_CODE]: The skill does not contain any scripts, command-line executions, or automation logic. It functions purely as a prompt-based persona.
- [PROMPT_INJECTION]: There are no instructions that attempt to bypass safety filters or override the system prompt. The Jacob Ham persona is implemented with clear boundaries and safety guardrails regarding medical advice and self-harm.
- [DATA_EXFILTRATION]: No network calls, file system access, or credential usage patterns were detected. The skill operates entirely within the chat context.
Audit Metadata