aruba-cx-system

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to execute a local Python script at mcp-servers/aruba-cx-mcp/aruba_cx_mcp_server.py to serve as its MCP server. This allows the agent to communicate with the Aruba CX REST API.
  • [PROMPT_INJECTION]: The skill ingests data from external network switches, creating a potential surface for indirect prompt injection via device-controlled fields.
  • Ingestion points: Switch metadata, firmware versions, and VSF topology retrieved via API (SKILL.md).
  • Boundary markers: None specified to differentiate between switch data and system instructions.
  • Capability inventory: Read-only tools for system and topology discovery (SKILL.md).
  • Sanitization: No explicit sanitization or validation of switch-provided strings is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — aruba-cx-system