remotion-render

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external resources for installation and configuration, including a CLI installation guide hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md and instructs users to add the belt-sh/cli skill.
  • [COMMAND_EXECUTION]: The skill relies on the belt CLI tool to execute video rendering jobs. It provides examples of using belt login and belt app run to interact with the backend service.
  • [DYNAMIC_EXECUTION]: The skill's primary functionality is to execute and render user-provided React (TSX) code strings using the Remotion framework. This is the intended purpose of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary React code strings which provides an ingestion surface for potential instructions embedded in processed data.
  • Ingestion points: The code parameter within the input schema of the remotion-render app.
  • Boundary markers: None identified in the prompt interpolation process.
  • Capability inventory: Uses Bash(belt *) to interact with the inference.sh platform and execute rendering logic.
  • Sanitization: No specific sanitization or validation of the input code string is described in the skill metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — remotion-render