policy-drafting

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a structured workflow for generating legal policy drafts based on regional jurisdictions in China. No network calls, remote code downloads, or credential-accessing patterns were identified.
  • [SAFE]: The skill processes content from local files (matter.md and CLAUDE.md). While this represents an ingestion surface, the skill lacks the capabilities (such as network access or shell execution) required for high-impact indirect prompt injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:07 AM
Security Audit — agent-trust-hub — policy-drafting