ad-creative

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and provide integration examples for numerous well-known AI platforms and APIs, such as Google Gemini, ElevenLabs, OpenAI, and Flux. These references are informative and point to official services.
  • [COMMAND_EXECUTION]: The skill includes instructions for interacting with local CLI tools (e.g., node tools/clis/google-ads.js) to retrieve performance data. This functionality is intended for use within the user's local development or marketing environment.
  • [REMOTE_CODE_EXECUTION]: Technical documentation within the skill references developer workflows such as using npx for Remotion and git clone for the Voicebox project. These are standard procedures for setting up the required tooling and are not executed automatically by the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where it processes external advertisement performance data (CSV or pasted text). While no specific boundary markers are defined for this data, the scope of the agent's actions (generating ad copy) minimizes the risk of malicious instruction execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:55 PM