netryx-street-level-geolocation
Warn
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation process requires cloning a repository from an unverified GitHub user account ('sparkyniner/Netryx-OpenSource-Next-Gen-Street-Level-Geolocation').- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the LightGlue library directly from a remote GitHub repository ('cvg/LightGlue.git') rather than a standard package registry.- [REMOTE_CODE_EXECUTION]: The workflow relies on executing downloaded Python scripts ('test_super.py', 'build_index.py') that manage network data, perform complex image processing, and write to the local file system.- [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands for environment setup, dependency management, and tool invocation, including 'pip install', 'brew install', and 'python' script execution.- [EXTERNAL_DOWNLOADS]: Fetches image tiles and panoramas from Google Street View's official services using the 'requests' library.- [REMOTE_CODE_EXECUTION]: Processes external image data through high-capability vision models (CosPlace, ALIKED, LightGlue) to determine geographic coordinates.
- Ingestion points: Processes user-uploaded street photos and panorama tiles downloaded via network requests.
- Boundary markers: No specific boundary markers or 'ignore' instructions are provided for the image processing pipeline.
- Capability inventory: Performs network requests, writes large-scale index data to local storage ('index/'), and executes deep learning inference.
- Sanitization: No explicit sanitization or validation logic is documented for the image files processed by the engine.
Audit Metadata