aruba-cx-interfaces

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script at mcp-servers/aruba-cx-mcp/aruba_cx_mcp_server.py using python3. This script functions as an MCP server to provide the monitoring tools. This is the intended operation of the skill.
  • [DATA_EXFILTRATION]: Authentication is managed through environment variables (ARUBA_CX_TARGETS) or a local configuration file (ARUBA_CX_CONFIG). These are standard, non-malicious methods for supplying credentials to automation tools without hardcoding them.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (such as target device names and interface IDs) to populate tool parameters.
  • Ingestion points: User queries for switch and interface information in SKILL.md examples.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: Executes local Python subprocesses for switch interaction.
  • Sanitization: Not explicitly described in the markdown body, but the tool schema provides structure for inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — aruba-cx-interfaces