The Agent Skills Directory

[SAFE]: No malicious patterns, command execution, or remote code downloads were detected. The skill functions as a design utility for generating static configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided parameters to generate design tokens. While this represents an ingestion point for untrusted data, the risk is minimal as the output is restricted to CSS and JSON configuration.
Ingestion points: User input parameters hex-color and project-type defined in SKILL.md.
Boundary markers: None explicitly defined.
Capability inventory: The agent writes a .forge.json configuration file to the local file system.
Sanitization: None specified in the instructions.

forge-init