naver-land-scouter

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a command-line interface in scripts/cli.py to orchestrate various real estate data processing tasks, including listing searches and property comparisons.
  • [EXTERNAL_DOWNLOADS]: Browser automation for session management is performed using Playwright, which standardly requires the installation of browser binaries from a trusted source.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external web content.
  • Ingestion points: Data enters the system via API endpoints defined in scripts/naver_land_repository.py and services in scripts/services/.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill utilizes network access for API calls and provides a CLI for data interaction.
  • Sanitization: While Pydantic is used for structural validation in scripts/schemas.py, there is no specific sanitization of the retrieved text for LLM instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 09:21 AM