The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized system access commands were detected in the skill files.
[PROMPT_INJECTION]: The skill is designed to process external data (user-provided code, screenshots, and text briefs) for typography analysis. Ingestion points: Data enters through the analysis of code blocks and visual elements in SKILL.md. Boundary markers: There are no explicit instructions for delimiters to separate user input from system instructions. Capability inventory: The skill only generates textual critiques and plans; it has no access to shell commands, network operations, or file system writes. Sanitization: No explicit sanitization or filtering of input content is specified. Due to the complete absence of dangerous capabilities, the risk associated with this ingestion surface is considered safe.

typeset