manim-composer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, templates, and instructional workflows. It does not contain any executable code, scripts, or automated triggers for dangerous operations.
- [COMMAND_EXECUTION]: The workflow specifies using 'web search' for researching mathematical concepts. This is a standard, safe tool application for information gathering within an AI agent's operational scope.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided concepts for visualization. While this is an input surface, the generated output is a structured markdown file (scenes.md) intended for human review and planning, and does not feed into any privileged execution environment.
- [METADATA_POISONING]: The skill's name, description, and metadata accurately reflect its functionality as a composition tool for animations.
Audit Metadata