Skills
skills/qu-skills/skills/remotion-render/Gen Agent Trust Hub

remotion-render

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches installation documentation from an external GitHub repository (inference-sh/skills).
  • [REMOTE_CODE_EXECUTION]: Directs users to install the belt-sh/cli tool and executes remote application logic on the inference.sh infrastructure.
  • [COMMAND_EXECUTION]: Utilizes the belt CLI tool to perform system-level operations for video rendering.
  • [PROMPT_INJECTION]: The skill ingests and processes user-provided React/TSX code, which serves as an attack surface for indirect prompt injection.
  • Ingestion points: The code parameter in the input schema within SKILL.md.
  • Boundary markers: None are defined in the provided usage examples to delimit the code from other instructions.
  • Capability inventory: The skill has access to the shell via the belt CLI and performs network operations to send code to a remote rendering service.
  • Sanitization: There is no evidence of sanitization or structural validation performed on the input code before it is passed to the execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:37 PM
Security Audit — agent-trust-hub — remotion-render