The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and documentation. No executable scripts, binaries, or configuration files that could carry out malicious actions are included.
[INDIRECT_PROMPT_INJECTION]: The skill's workflow involves processing untrusted external source code (HTML, CSS, and JS), which represents an indirect prompt injection surface. However, the risk is negligible as the skill provides no automated capabilities or scripts to exploit this surface.
Ingestion points: The "Inputs" section of SKILL.md identifies HTML, CSS, and JS as primary inputs.
Boundary markers: No specific delimiters or instructions to ignore embedded malicious directives are defined.
Capability inventory: The skill does not define any scripts, executable tools, or network operations.
Sanitization: No input validation or sanitization procedures are specified for the processed code.
[SAFE]: A thorough review of the metadata and instructions found no evidence of prompt injection, obfuscation, or other malicious patterns. The content matches the stated purpose of UI/UX transformation.

krds-transform