The Agent Skills Directory

[SAFE]: The skill provides instructional content for accessibility standards (WCAG 1.2.2, 1.4.3, 2.3.1) and broadcast practices. The instructions do not contain prompt injection or attempts to bypass safety filters.
[COMMAND_EXECUTION]: The skill includes a Node.js script (scripts/caption-cps.mjs) designed to be run locally. Analysis of the script shows it performs basic arithmetic and string length checks on JSON data. It uses the built-in node:fs module to read a local file and does not perform network operations, dynamic code execution (eval/exec), or access sensitive system paths.
[DATA_EXPOSURE]: The validation script reads a user-provided JSON file (cues.json). There is no evidence of hardcoded credentials, sensitive file access, or data exfiltration to external domains.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external sources. All logic is contained within the provided script and instructions.

accessibility-lead