The Agent Skills Directory

[SAFE]: The skill employs local Python scripts (render_wireframe.py and validate_wireframe.py) to handle the logic of processing wireframe data. These scripts use standard libraries and perform only local file operations necessary for their described tasks.
[SAFE]: The skill implements a security boundary for external content. In instructions/create.md and instructions/discovery.md, it explicitly instructs the agent to treat fetched pages or briefs as passive input and to ignore any embedded directives, which effectively mitigates indirect prompt injection risks.
[SAFE]: No obfuscation, hardcoded credentials, or unauthorized network operations were detected in the skill's instructions or scripts.

wireframe-sketch