meraki-switch-ops

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill documentation describes workflows that ingest data from external Meraki device APIs, which constitutes a surface for indirect prompt injection. \n
  • Ingestion points: Data is pulled from getDeviceSwitchPorts, getDeviceSwitchPortStatuses, getSwitchVlans, and getDeviceSwitchAccessControlLists. \n
  • Boundary markers: No delimiters or isolation instructions are specified in the skill body to distinguish between system instructions and external data. \n
  • Capability inventory: The skill utilizes write-capable tools such as updateDeviceSwitchPort, cycleDeviceSwitchPorts, createSwitchVlan, updateDeviceSwitchAccessControlLists, and createDeviceSwitchQosRule. \n
  • Sanitization: No data sanitization or validation steps are documented within the administrative workflows to handle potentially malicious content in device metadata. \n- [SAFE]: The skill references the CiscoDevNet/meraki-magic-mcp-community GitHub repository for its server component, which is an official resource from a well-known networking technology provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM