manim-video
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow involves generating and executing local Python scripts using the Manim library and performing video post-processing with ffmpeg. These commands are integral to the skill's primary purpose of video production.
- [SAFE]: The setup script (scripts/setup.sh) is restricted to verifying the versions and presence of local prerequisites (Python, Manim, LaTeX, and ffmpeg) and does not perform any remote code execution or untrusted downloads.
- [SAFE]: No evidence of malicious patterns such as credential harvesting, data exfiltration, persistence, or prompt obfuscation was found in the skill's instructions or supporting reference documents.
- [SAFE]: The skill implements a rigorous planning phase ('PLAN' step) that requires the agent to document the narrative and visual structure in a plan.md file before generating executable code, reducing the risk of accidental or malicious code generation.
Audit Metadata