The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external project context from local files to inform its planning advice. If these files are maliciously crafted, they could influence the agent's output.
Ingestion points: The skill instructs the agent to read context from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md as specified in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the ingested file content.
Capability inventory: The skill's primary capabilities are generating text-based planning advice and Mermaid diagrams. It does not request access to high-privilege tools such as shell execution or network writing in its configuration.
Sanitization: The instructions do not define sanitization or validation logic for the content of the referenced context files.
[SAFE]: The skill consists entirely of architectural best practices, templates, and design patterns. All referenced resources and external links are for documentation purposes and do not involve remote code execution or automated installations.

site-architecture