ads-optimize
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of natural language instructions without any embedded code, scripts, or external downloads.
- [SAFE]: The instructions incorporate robust safety constraints, specifically defining a 'Destructive-action boundary' that prevents the agent from performing permanent deletions of campaigns, ad groups, or audiences, requiring reversible alternatives instead.
- [SAFE]: The skill requires evidentiary support (search terms reports, business-relevance evidence) before taking action on search terms, preventing the invention of arbitrary negative keywords.
- [SAFE]: No evidence of obfuscation, credential harvesting, or unauthorized network access was detected in the skill's content.
Audit Metadata