The Agent Skills Directory

[No Code] (SAFE): The skill consists exclusively of documentation and examples. There are no scripts, binaries, or command-line instructions provided.
[Data Exposure] (SAFE): The skill reads from a local context file (.claude/product-marketing-context.md) to inform its suggestions, which is a standard pattern for personalizing AI outputs and does not involve exfiltration or unauthorized access to sensitive system files.
[Indirect Prompt Injection] (SAFE): While the skill processes user-provided information to generate schema, it lacks the capabilities (such as network access or file-writing) that would make such an injection dangerous. The output is intended to be human-reviewed JSON-LD markup.

schema-markup