The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or unauthorized data exfiltration behaviors were identified during the analysis of the skill's instructions and reference files.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to download the official Runpod MCP server from the npm registry (@runpod/mcp-server) and connect to the author's hosted infrastructure at mcp.runpod.io. These are legitimate vendor-controlled resources.
[CREDENTIALS_UNSAFE]: Sensitive information such as the RUNPOD_API_KEY is managed via environment variables and OAuth placeholders, which is the recommended secure practice for avoiding hardcoded secrets.
[COMMAND_EXECUTION]: The skill includes shell commands for environment setup and diagnostic probing of the MCP server version. These commands are transparent, use official endpoints, and are intended for legitimate configuration purposes.

runpod-mcp