my-legal-researcher

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates legal research by querying official Korean government domains, including the National Law Information Center (law.go.kr), the Supreme Court (glaw.scourt.go.kr), and the Ministry of Government Legislation (moleg.go.kr).
  • [PROMPT_INJECTION]: The skill processes external data from web searches, which presents a structural indirect prompt injection surface. 1. Ingestion points: Web search results retrieved in STEP 2. 2. Boundary markers: Absent from the search result interpolation. 3. Capability inventory: The skill is restricted to web search and text-based report generation. 4. Sanitization: No explicit content filtering is implemented. The risk is minimal as the skill targets institutional sources and lacks dangerous output capabilities like file system writes or command execution.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local credentials, environment variables, or private configuration files. Network operations are limited to search queries based on user-provided legal topics.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 11:37 PM
Security Audit — agent-trust-hub — my-legal-researcher