The Agent Skills Directory

[SAFE]: The skill performs legitimate text extraction and local file management for the purpose of maintaining a domain glossary.
[DATA_EXPOSURE]: The skill reads and writes to a local file named UBIQUITOUS_LANGUAGE.md. This is the primary function of the skill and does not target sensitive system files or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill processes user conversation data to extract terms. While this presents a surface for indirect prompt injection, the skill lacks dangerous capabilities (such as network access or shell execution) that could be exploited via this vector. The output is formatted as Markdown text.

ubiquitous-language