The Agent Skills Directory

[SAFE]: A thorough analysis of all skill files, including instructions, metadata, and scripts, found no evidence of malicious intent, obfuscation, or unauthorized operations.
[INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points in project configuration and source files (package.json, tsconfig.json, src/**) to perform architectural analysis. Although it lacks explicit boundary markers or input sanitization, the skill's capability inventory is limited to read-only and search operations (Read, Glob, Grep, WebFetch, WebSearch), which prevents the execution of high-risk actions such as file modification or command execution.
[EXTERNAL_DOWNLOADS]: The skill references documentation and templates from trusted organizations and well-known services, such as FastAPI (Tiangolo), Next.js (Vercel), and standard testing frameworks like Pytest and Vitest. These references are used for educational and guidance purposes and do not facilitate the execution of untrusted remote code.

architecture-patterns