archimate-modeling

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Command Execution (SAFE): The skill defines a specific set of operations for the archicli utility. These commands are restricted to architecture modeling tasks such as querying models, creating elements, and exporting views. No arbitrary or high-risk shell commands were found.
  • Network Operations (SAFE): The skill defaults to http://127.0.0.1:8765 for its API server communication. This local-only traffic does not involve external data exfiltration or communication with untrusted remote hosts.
  • Data Exposure (SAFE): While the skill manages model data, it does not access sensitive system paths (like SSH keys or cloud credentials) and maintains model state in local JSON files.
  • Indirect Prompt Injection (SAFE): The skill processes Bill of Materials (BOM) files. It includes a verify step with --semantic checks, which serves as a validation layer for the structured JSON data it ingests.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:41 PM