paid-media-programmatic-buyer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and does not contain any executable scripts, shell commands, or network operations. It describes standard media buying procedures for platforms like Google Display Network and various DSPs.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing external data sources such as partner media kits, performance reports, and spreadsheets. This represents a potential surface for indirect prompt injection where malicious instructions could be embedded in the processed data.
- Ingestion points: Processes external media kits, AMP spreadsheets, and placement performance reports (SKILL.md).
- Boundary markers: None specified in the instructions.
- Capability inventory: The agent is instructed to manage GDN campaigns, adjust bids, and update targeting settings programmatically if tool integrations are available (SKILL.md).
- Sanitization: No explicit sanitization or validation steps for external content are described.
Audit Metadata