The Agent Skills Directory

[SAFE]: No security issues detected. The skill is purely instructional and does not perform network operations, file system modifications, or code execution.
[DATA_EXFILTRATION]: No exfiltration risks were identified. The skill's primary function is a privacy-enhancing task: the de-identification and anonymization of sensitive internal text to prevent data leakage during sharing.
[PROMPT_INJECTION]: While the skill processes untrusted input text, it lacks any high-risk capabilities (such as shell access or network requests) that could be leveraged if an indirect prompt injection were attempted within the input data.
[NO_CODE]: The skill consists only of documentation and prompt instructions; no executable scripts or external dependencies are included.

decontextualize-text