ad-creative

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external performance data from sources such as CSV files or API outputs to iterate on ad copy. This creates a surface for untrusted content ingestion, which is handled as a core functional requirement.
  • [DYNAMIC_EXECUTION]: Video creative is generated programmatically using the Remotion framework, which utilizes React-based templates and data feeds to produce deterministic video assets at scale.
  • [REMOTE_CODE_EXECUTION]: Reference materials include documentation for standard third-party generative AI services (e.g., Google Gemini, OpenAI, ElevenLabs) and reputable open-source repositories (e.g., Voicebox by Jamie Pine) to assist in asset production.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:39 PM