The Agent Skills Directory

[SAFE]: The skill does not contain any malicious patterns, obfuscation, or unauthorized access attempts. It follows best practices for providing instructional content and code examples related to SEO and structured data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests information from the user (e.g., page content, business goals) and optionally reads local context files (.agents/product-marketing-context.md) to generate schema markup. This represents a standard surface for indirect injection, but the risk is minimal given the skill's capabilities.
Ingestion points: User input via prompts and the local .agents/product-marketing-context.md file (identified in SKILL.md).
Boundary markers: None identified.
Capability inventory: Limited to text generation (JSON-LD markup). No file-write, network, or command execution capabilities are utilized by this skill.
Sanitization: None identified.
[EXTERNAL_DOWNLOADS]: The skill references well-known and trusted services, including Google's Rich Results Test and the Schema.org Validator, for the purpose of validating generated structured data. These references are documented neutrally as they point to official industry-standard tools.

schema-markup