manim-visualizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious patterns, exfiltration, or persistence mechanisms were detected. The skill is dedicated to mathematical animation and video rendering.
- [Indirect Prompt Injection] (LOW): The skill processes untrusted agent names and task JSON data to generate text overlays in animations, creating a minor surface for indirect injection.
- Ingestion points: CLI arguments
--agentsand--tasksinscripts/generate.py. - Boundary markers: Absent; text is rendered directly as provided by the caller.
- Capability inventory: Local file system write access for MP4 video generation.
- Sanitization: Minimal; task labels are truncated to 20 characters in
scripts/base.py.
Audit Metadata