ad-creative

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known and established technology services for generating ad visuals and audio, including Google (Gemini, Veo), OpenAI (Sora, TTS), and ElevenLabs. These external resources are documented as part of the skill's core functionality for creative production.
  • [COMMAND_EXECUTION]: The skill documentation includes examples of using internal command-line tools (e.g., google-ads.js) to fetch performance reports. These operations are intended for data-driven creative iteration and are executed within the agent's controlled environment.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze performance data (such as CSV or API outputs) to identify winning creative patterns. This constitutes an ingestion point for untrusted data; however, the skill's instructions focus on structured metric analysis and thematic iteration, which is a standard and low-risk use case for this type of agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:35 AM
Security Audit — agent-trust-hub — ad-creative