chinese-legal-privacy

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses local configuration files stored in ~/.claude/plugins/config/ and ~/.codex/legal-zh/privacy-legal/ to read and maintain user practice profiles. This is used for personalizing legal drafting workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external instructions from local project files (such as privacy-legal/CLAUDE.md). It mitigates associated risks by explicitly instructing the agent that all output must be treated as draft work requiring human lawyer review and that all legal citations must be verified from current, reliable sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:43 AM
Security Audit — agent-trust-hub — chinese-legal-privacy