The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the @runpod/mcp-server package from the official npm registry, which is a well-known service. These tools are provided by the official vendor 'runpod'.
[COMMAND_EXECUTION]: The skill utilizes shell commands like npx for installation and curl for verifying connectivity to the hosted API at https://mcp.getrunpod.io/. These operations are consistent with the skill's primary purpose of infrastructure management.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external tool outputs returned by the Runpod REST API.
Ingestion points: Untrusted data enters the agent context through tool outputs including list-endpoints, stream-logs, and cost breakdowns.
Boundary markers: None explicitly defined in the provided markdown instructions.
Capability inventory: The skill possesses capabilities to perform infrastructure CRUD operations (creating and deleting pods/endpoints) and executing shell commands via the allowed Bash tools.
Sanitization: There are no documented sanitization or validation steps for the content returned by the external API before it is processed by the agent.

runpod-mcp