ad-platform-selection
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured decision framework for paid media strategy. It uses business-specific inputs (AOV, margins, budget) to recommend ad channels. No malicious patterns, obfuscation, or unauthorized network operations were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest business data via a structured 'Interview' process to generate ad plans. It includes specific boundary markers through a defined output template and instructional constraints that separate the reasoning logic from user-provided data. The capability surface is limited to text generation and strategic recommendation based on internal arithmetic logic, with no evidence of unsafe tool interpolation or lack of sanitization.
Audit Metadata