skills/openai/plugins/remotion-saas/Gen Agent Trust Hub

remotion-saas

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill describes processes for ingesting dynamic metadata in player.md, creating a potential injection surface if data is unsanitized. 1. Ingestion points: Dynamic props in player.md. 2. Boundary markers: Absent. 3. Capability inventory: Video rendering via headless browsers and AWS Lambda (rendering.md). 4. Sanitization: Not specified.
  • [Credential Management Best Practices]: The skill includes explicit security advice in rendering.md to use environment variables for AWS secrets and avoid direct input into chat.
  • [Command Execution]: Development and rendering workflows use npx remotion commands, which interact with the shell environment.
  • [External Resource Integration]: Links to official templates and documentation on remotion.dev and GitHub are used appropriately for the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 11:18 AM
Security Audit — agent-trust-hub — remotion-saas