The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and provides installation instructions for an external tool hosted on the official CiscoDevNet GitHub repository (github.com/CiscoDevNet/meraki-magic-mcp-community). As Cisco is a well-known technology provider, this source is considered reputable.
[CREDENTIALS_UNSAFE]: Sensitive information such as MERAKI_API_KEY and MERAKI_ORG_ID is correctly handled through the use of environment variables rather than being hardcoded in the instructions or scripts.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests external data that could contain malicious instructions.
Ingestion points: Data is retrieved from the Cisco Meraki API through various methods like getOrganizations, getNetworks, and getNetworkClients (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within the API responses.
Capability inventory: The skill includes powerful write operations such as rebootDevice, deleteNetwork, createOrganizationAdmin, and removeDevice (SKILL.md).
Sanitization: The instructions do not mention sanitization or validation of the data returned from the Meraki API before it is processed by the agent.

meraki-network-ops