paid-media-programmatic-buyer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a persona definition and instruction set for programmatic advertising tasks. It does not perform any suspicious network operations, credential harvesting, or unauthorized file system access.
- [NO_CODE]: No executable scripts or binary files are distributed with this skill. It relies on natural language instructions and existing platform tools (Google Ads MCP/API) for its operations.
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing external media reports and partner data, which presents a surface for indirect prompt injection. This risk is managed by the platform's tool safety and is inherent to the task of analyzing external data.
- Ingestion points: Placement performance reports, industry publication media kits, and ABM account lists.
- Boundary markers: None specified in the prompt instructions.
- Capability inventory: Capability to use Google Ads tools to adjust bids and update placement exclusion lists.
- Sanitization: No explicit instructions for sanitizing or escaping the content of processed reports.
Audit Metadata