mmk-threads-insights
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes a vendor-provided CLI tool ('mmk') to fetch account metrics. The execution environment is restricted to this specific tool via the 'allowed-tools' configuration.
- [SAFE]: Analysis of the instructions and metadata revealed no evidence of prompt injection, data exfiltration, or obfuscation. The skill primarily processes structured numeric and categorical data (analytics), which minimizes the surface area for indirect prompt injection.
Audit Metadata