remotion-render

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests raw React/TSX code as input which is then transmitted to a remote environment for rendering, presenting a surface where instructions embedded in the code could influence the agent or the remote compute environment.\n
  • Ingestion points: The code parameter within the input schema defined in SKILL.md.\n
  • Boundary markers: Absent. The skill does not provide instructions or delimiters for the agent to isolate user-provided code from the execution context.\n
  • Capability inventory: The skill utilizes the belt CLI to perform network requests and execute code on the inference.sh platform.\n
  • Sanitization: Absent. There is no evidence of validation or filtering for the code string input.\n- [EXTERNAL_DOWNLOADS]: The skill refers to and utilizes external utilities and scripts from the inference.sh platform.\n
  • Fetches CLI installation instructions from raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.\n
  • Recommends the installation of the belt-sh/cli Node.js package.\n
  • References the inferencesh Python SDK for programmatic usage.\n- [DYNAMIC_EXECUTION]: The primary function of the skill is to take dynamic TSX component code provided at runtime and execute it within a remote rendering engine via the belt CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:26 AM