remotion-render

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to interact with the rendering service. Access is limited to the belt command through the allowed-tools frontmatter, ensuring least privilege.- [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for installing the belt-sh/cli and refers to the inferencesh Python SDK. These are legitimate tools for the referenced platform.- [REMOTE_CODE_EXECUTION]: The skill is designed to send React TSX code to the inference.sh service for server-side rendering into MP4 files. This remote execution is the primary functionality of the skill.- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface to ingest React code for video generation, creating a potential surface for indirect injection if provided with malicious code.
  • Ingestion points: The code parameter within the input schema in SKILL.md.
  • Boundary markers: The TSX code is passed as a string value in a JSON payload to the belt CLI.
  • Capability inventory: The agent can execute shell commands via the belt binary.
  • Sanitization: No explicit sanitization or validation of the input TSX code is described in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:40 PM
Security Audit — agent-trust-hub — remotion-render