manim-video

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to take user-supplied concepts or algorithm descriptions and translate them into executable Manim Python scripts. This represents an indirect prompt injection surface where a malicious user prompt could attempt to influence the generated code to perform unauthorized actions within the agent's execution environment.
  • Ingestion points: User prompts describing concepts, equations, or algorithms (SKILL.md).
  • Boundary markers: The instructions do not explicitly require the use of boundary markers or
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 12:47 PM
Security Audit — agent-trust-hub — manim-video