The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill is designed for organizational and documentation purposes.
[PROMPT_INJECTION]: The skill processes untrusted user data from the conversation. While this creates an indirect prompt injection surface, there are no dangerous capabilities (such as network access or privileged command execution) that could be exploited. The ingestion point is the conversation history (SKILL.md), and the primary capability is writing a terminology file (UBIQUITOUS_LANGUAGE.md). Boundary markers and sanitization are absent, but the scope of the skill's operations is limited to local file generation within the workspace.

ubiquitous-language