inboundfy-personas
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the local project scope, managing marketing personas by interacting with files in the .inboundfy/ directory and processing user interviews.
- [SAFE]: No external network communication, remote script downloads, or command execution patterns were detected.
- [SAFE]: Instructions are focused on data structure and marketing logic, with no evidence of prompt injection or obfuscation.
- [SAFE]: While the skill processes external input (Category 8), the lack of exploitable tools (e.g., shell, network) renders the attack surface minimal and safe for standard agent use.
Audit Metadata