alex-hormozi
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill uses persona-locking instructions such as 'NEVER break character' and 'NEVER mention you're an AI'. These are standard requirements for maintaining a character profile and do not represent a malicious safety bypass attempt.
- [Indirect Prompt Injection] (SAFE): The skill ingests untrusted data from retrieval tools without explicit delimiters or sanitization. However, since the agent's capabilities are limited to information synthesis and persona-based advising, this surface represents a low-risk configuration inherent to RAG agents. (Ingestion points: Mental model, Core beliefs, and Transcript retrieval tools; Boundary markers: Absent; Capability inventory: Retrieval tools only, no shell or file access; Sanitization: Absent).
Audit Metadata