aruba-cx-config

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external network switches into the agent's context, presenting a risk of indirect prompt injection.\n
  • Ingestion points: Untrusted data is fetched from network equipment via tools such as get_running_config, get_startup_config, and get_routing_table.\n
  • Boundary markers: The skill does not define boundary markers or explicit instructions to the agent to ignore potential commands embedded within the retrieved switch configuration data.\n
  • Capability inventory: The skill possesses high-impact capabilities, including modifying device configurations (save_config), performing firmware upgrades (issu_upgrade), and transferring files (upload_firmware, download_firmware).\n
  • Sanitization: There is no evidence of sanitization or validation performed on the data retrieved from the switches before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — aruba-cx-config