expansion-kickoff
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to facilitate labor expansion planning through information gathering and structured analysis. It does not exhibit malicious patterns such as credential theft, data exfiltration, or unauthorized command execution.
- [SAFE]: File system interactions are localized to the skill's own configuration workspace in the user's home directory (~/.claude/plugins/config/claude-for-legal-zh/employment-legal/). This is standard behavior for maintaining state and configuration for such tools.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface by processing untrusted user input regarding employment needs to generate files and checklists.
- Ingestion points: User-provided inputs such as region names and employment demand details defined in
SKILL.md. - Boundary markers: None identified; user input is not explicitly delimited from the system instructions.
- Capability inventory: Reading and writing files in the plugin's configuration directory.
- Sanitization: None identified; the skill assumes the provided data is for documentation and planning purposes without additional validation.
Audit Metadata