The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscated content were detected within the skill documentation.- [COMMAND_EXECUTION]: The skill documents the use of the runcomfy CLI to interact with the RunComfy Model API. This is a legitimate use of command-line tools for the skill's stated purpose.- [EXTERNAL_DOWNLOADS]: The skill references the @runcomfy/cli package from the npm registry as a prerequisite. RunComfy is a well-known service for hosting AI models.- [CREDENTIALS_UNSAFE]: The skill provides instructions for managing API tokens using environment variables (RUNCOMFY_TOKEN) or configuration files with restricted permissions (0600), which follows security best practices for credential management.

wan-2-7