The Agent Skills Directory

[SAFE]: No security issues were detected. The skill instructions are focused on structured data implementation and provide standard implementation templates.- [EXTERNAL_DOWNLOADS]: The skill provides links to official validation tools from well-known services, including Google and Schema.org.- [DATA_EXFILTRATION]: The skill instructs the agent to read local project context from .agents/product-marketing-context.md. This is a standard mechanism for context-sharing in agentic workflows and does not involve unauthorized data access or external transmission.- [PROMPT_INJECTION]: The skill ingests data from local context files (Ingestion points: .agents/product-marketing-context.md) without explicit boundary markers or sanitization. However, the skill does not possess exploitable capabilities such as subprocess execution or network operations, limiting the risk of indirect prompt injection.

schema-markup