ad-copy

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions guiding the AI to generate ad copy variants based on user inputs.
  • [NO_CODE]: No scripts, configuration files, or executable code are present in the skill package.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data (Product & offer, Audience, etc.) into the prompt context. However, the skill lacks any dangerous capabilities—it has no file system access, network connectivity, or subprocess execution capabilities—making the risk negligible.
  • [TRUST-SCOPE-RULE]: The skill does not reference any external URLs, repositories, or dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:25 PM
Security Audit — agent-trust-hub — ad-copy