Skills
skills/gooseworks-ai/gooseworks-ads-skills/create-split-screen-creator-ad/Gen Agent Trust Hub

create-split-screen-creator-ad

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python script (references/assemble.py) that orchestrates video assembly by executing ffmpeg and ffprobe via the subprocess module. These calls use argument lists rather than shell strings, which is a secure practice that prevents shell injection attacks.
  • [DATA_EXFILTRATION]: The script reads media files and configuration data from local paths specified in an ad-spec.json file. The file access is restricted to the resources required for video processing, with no evidence of sensitive data harvesting or unauthorized network transmission.
  • [PROMPT_INJECTION]: The skill processes user-provided briefs to generate ad content. While this represents an ingestion point for untrusted data, the skill's downstream capabilities are limited to media processing with FFmpeg, posing no significant risk to the agent's core instructions or safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:07 PM
Security Audit — agent-trust-hub — create-split-screen-creator-ad