The Agent Skills Directory

[SAFE]: The skill consists of markdown instructions without any bundled scripts, configuration files, or external dependencies. No malicious patterns were identified during the analysis of the provided content.\n- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by requiring the agent to read untrusted design artifacts and codebase content. Ingestion points include local files such as design/system.md, design/entities/{entity}/ux.md, and the general repository codebase. No specific boundary markers or sanitization logic are defined in the instructions. However, this behavior is essential for the skill's purpose as a coding assistant, and no explicit malicious instructions were found within the skill itself.

ixlab-engineer