orthographic-registration
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a Python script (
scripts/register_views.py) to process image files and generate a registration report. The logic is restricted to mathematical calculations and image metadata extraction using standard libraries. - [DATA_EXFILTRATION]: No network access or attempts to access sensitive files (e.g., SSH keys, cloud credentials) were found. The script only reads provided image paths and writes a local JSON file.
- [PROMPT_INJECTION]: The skill handles external image files which could potentially contain malicious content. However, the processing script only extracts numerical properties and bounding box data, minimizing the risk of instructions within the images influencing agent behavior.
- [SAFE]: The skill's behavior is consistent with its documentation. It uses well-known libraries and provides a clear utility for 3D artists without introducing hidden or dangerous functionality.
Audit Metadata