The Agent Skills Directory

[SAFE]: The skill provides a procedural framework for language audit and correction. It utilizes an iterative loop to ensure that edits in one section of text do not introduce new issues in others. No evidence of prompt injection, data exfiltration, or malicious execution was found. The instructions are transparent about token costs and explicitly direct the agent to warn users when processing large files. References to local scripts like thai-route.sh are standard for workflow integration and do not involve remote code execution from untrusted sources.

kode-thai