meraki-network-ops
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to Cisco's official Meraki MCP server at
https://mcp.meraki.com/mcpand references the official CiscoDevNet GitHub repository for self-hosting. These are well-known and trusted services provided by Cisco for their ecosystem. - [CREDENTIALS_UNSAFE]: The skill requires a
MERAKI_DASHBOARD_API_KEYto function. It explicitly instructs the user to use a read-only key, which is a standard security practice to minimize risk. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Meraki API endpoints, including organization names, network settings, and client data. While this data could theoretically contain malicious instructions (indirect injection), the skill is strictly read-only and lacks the capabilities to perform dangerous operations like file writes or command execution, neutralizing the risk.
- [COMMAND_EXECUTION]: The skill specifically excludes all 431 mutating Meraki operations (POST, PUT, DELETE), ensuring that it cannot be used to make unauthorized changes to the network infrastructure.
Audit Metadata