The Agent Skills Directory

[SAFE]: The skill is primarily instructional and generative, producing static JSON-LD code blocks based on user input and local context files.
[SAFE]: References to external tools are limited to official, well-known services including Google's Rich Results Test and the Schema.org Validator.
[SAFE]: While the skill reads local context files such as .agents/product-marketing-context.md, this behavior is scoped to gathering information for the intended task and does not involve exfiltrating data to external sources.
[SAFE]: No obfuscation, remote code execution, or privilege escalation patterns were detected across the skill files.

schema-markup