The Agent Skills Directory

[SAFE]: The skill instructions and reference materials were analyzed for malicious patterns, including prompt injection, data exfiltration, and obfuscation. No security risks were identified. The skill is purely consultative, providing templates (Mermaid, ASCII) and guidelines for information architecture. While it instructs the agent to ingest local project context files (e.g., .agents/product-marketing.md), it does not possess or utilize any high-risk capabilities such as network access, file system modification, or command execution that would present a vulnerability surface for indirect prompt injection.

site-architecture