The Agent Skills Directory

[SAFE]: The skill is purely instructional, providing a persona and templates for information architecture tasks without involving any scripts or code execution.
[SAFE]: No external network requests, data exfiltration patterns, or hardcoded credentials were detected.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface through local context files but is evaluated as safe because it lacks any dangerous capabilities. Ingestion points: SKILL.md reads .agents/product-marketing-context.md. Boundary markers: Absent. Capability inventory: No subprocess calls, network operations, or file-write capabilities were found. Sanitization: Absent.

site-architecture