05-copy-quang-cao

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a template-driven copywriting assistant that generates advertisement variations based on marketing frameworks (e.g., AIDA, PAS). It incorporates platform-specific constraints for Meta, TikTok, and Google Ads, including character limits and compliance checks.
  • [SAFE]: Data ingestion is limited to local context files (.agents/product-marketing-context.md and .agents/personal-brand-context.md) and user-provided product details. The skill does not possess capabilities for network communication, file system modification, or command execution, ensuring that the processing of this data is restricted to text generation.
  • [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found. The skill references legitimate Vietnamese regulatory requirements (Decree 147/2024) for AI transparency, indicating a focus on compliance and best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:39 PM
Security Audit — agent-trust-hub — 05-copy-quang-cao