The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides a local Python script, scripts/job-description-generator.py, which is intended for validating drafted job descriptions. This script operates within the restricted allowed-tools environment, performing static analysis on local text input without any network activity, subprocess spawning, or dynamic code execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and screen resumes, which are untrusted external data sources. This constitutes an indirect prompt injection surface; however, the skill is structured to provide informational analysis rather than autonomous action, and it includes explicit instructions for human oversight and verification of all outputs.
[SAFE]: The skill exhibits high transparency through its optimization logs and metadata, documenting its development and compliance review cycles. All external links target official government portals, reputable legal databases, or well-known professional platforms. Static detector hits for instruction concealment are false positives triggered by legitimate safety and scoping instructions that guide the model away from providing unauthorized legal advice.

israeli-hr-recruitment-automator