The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of user-provided descriptions of work arrangements and outputs from legal research tools. While it lacks explicit boundary markers or input sanitization, the risk is neutralized by the skill's rigid, multi-step analytical workflow and mandatory confirmation prompts that prevent automated execution of embedded commands.
[DATA_EXFILTRATION]: The skill reads a local configuration file located at ~/.claude/plugins/config/claude-for-legal-zh/employment-legal/CLAUDE.md. This path is specific to the plugin's own configuration and does not access sensitive system credentials or personal data. No unauthorized network operations were observed.

worker-classification