Skills
skills/gooseworks-ai/gooseworks-ads-skills/remix-chatgpt-ad-from-sample/Gen Agent Trust Hub

remix-chatgpt-ad-from-sample

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local system utilities to perform video production tasks. This includes using ffmpeg for capturing thumbnails and encoding MP4 video exports, and npx playwright for recording a simulated browser environment. It also executes local Node.js scripts (node clips/record-master.js) to drive the rendering process.
  • [EXTERNAL_DOWNLOADS]: To satisfy environmental prerequisites, the skill guides the user to install system-level dependencies and browser binaries from well-known sources, specifically ffmpeg via package managers and playwright chromium binaries.
  • [PROMPT_INJECTION]: The skill derives new content from external inputs, including ad samples and brand research data. This creates a surface for indirect prompt injection where instructions could be embedded in the processed data. The skill mitigates this risk by implementing a mandatory human-in-the-loop approval gate (Phase 1.5) that requires the user to review the generated script before rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — remix-chatgpt-ad-from-sample