The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation references an external GitHub repository https://github.com/aiopnet/mcp-nautobot as the source for the underlying MCP server implementation.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from a Nautobot instance, which represents a potential attack surface for indirect prompt injection via user-controlled fields like object descriptions or hostnames.
Ingestion points: IPAM data retrieved through tools such as get_ip_addresses, get_prefixes, and search_ip_addresses.
Boundary markers: The skill instructions do not define specific delimiters or instructions for the agent to treat data retrieved from the API as untrusted.
Capability inventory: All tools are explicitly defined as read-only. The skill lacks dangerous capabilities such as writing to the file system, executing shell commands, or making arbitrary network requests.
Sanitization: There are no explicit mentions of data sanitization or validation of the content returned by the Nautobot API.

nautobot-sot