three-scope-map

Warn

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes multiple Python scripts such as 'resolve_map_data.py', 'generate_map_theme.py', 'apply_map_theme.py', and others that the agent is instructed to execute to process geographic data and generate map themes.
  • [COMMAND_EXECUTION]: The script 'apply_map_theme.py' utilizes 'importlib.util' to dynamically load and execute other local Python scripts ('generate_map_theme.py' and 'recolor_label_asset.py'). This dynamic loading from computed paths is a sensitive pattern used for coordinating internal utility scripts.
  • [EXTERNAL_DOWNLOADS]: The 'resolve_map_data.py' script and 'mapDataAdapter.ts' template fetch GeoJSON data from 'geo.datav.aliyun.com' and 'raw.githubusercontent.com'. While these are well-known services, the skill relies on this external data to generate its 3D geometry.
  • [PROMPT_INJECTION]: 'SKILL.md' contains strict instructions enforcing the use of provided templates ('Non-Negotiable One-To-One Rules') and the preservation of specific attribution comments. These instructions aim to constrain the agent's behavior to follow exact visual styles and maintain author credits.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 17, 2026, 10:06 AM
Security Audit — agent-trust-hub — three-scope-map