korean-law-search

Warn

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'korean-law-mcp' NPM package globally from a third-party source not identified as a trusted organization or well-known service.
  • [REMOTE_CODE_EXECUTION]: It relies on remote MCP server endpoints hosted at 'https://korean-law-mcp.fly.dev/mcp' and 'https://api.beopmang.org/mcp', which execute logic externally and return data that influences agent behavior.
  • [COMMAND_EXECUTION]: The skill operates by running local shell commands via the 'korean-law' CLI tool, allowing for execution of the installed package's logic on the host system.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8). 1. Ingestion points: Data is fetched from remote APIs ('korean-law-mcp.fly.dev' and 'api.beopmang.org') as specified in SKILL.md. 2. Boundary markers: The skill does not use delimiters or instructions to separate external legal text from agent commands. 3. Capability inventory: The skill has command execution capabilities through the 'korean-law' CLI. 4. Sanitization: There is no evidence of validation or sanitization of the remote content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 13, 2026, 01:00 AM
Security Audit — agent-trust-hub — korean-law-search