korean-law-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to download and install the core MCP server from the NPM registry (
npx korean-law-mcpornpm install -g korean-law-mcp). - [REMOTE_CODE_EXECUTION]: The skill provides instructions for cloning and executing code from an external GitHub repository (
https://github.com/chrisryugj/korean-law-mcp.git) to set up a local development environment. This involves runningnpm installandnpm starton unvetted external code. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input and external API data, creating a potential surface for indirect prompt injection.
- Ingestion points: The
verify_citationstool accepts arbitrary user-provided text (userText). Additionally, the skill fetches legal statutes, precedents, and ordinances from the external MOLEG API based on user queries. - Boundary markers: There are no explicit instructions or delimiters mentioned to prevent the agent from obeying instructions that might be embedded within the legal texts or API responses.
- Capability inventory: The skill possesses network access to interact with the Korean Ministry of Government Legislation (법제처) APIs and can ingest and return large volumes of legal text to the agent's context.
- Sanitization: No sanitization or filtering of the fetched legal content is described in the skill's instructions.
Audit Metadata