ad-creative-testing
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a planning and analysis guide for advertising campaigns. It does not include scripts, executables, or automated code execution. All external references point to reputable industry benchmarks, platform documentation, and informational blogs.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data in the form of exported ad metrics (CSV). While this creates a data processing surface, it is the primary intended function of the skill.
- Ingestion points: Exported ad metrics CSV files as mentioned in the compatibility section of
SKILL.md. - Boundary markers: Not explicitly defined within the prompt instructions.
- Capability inventory: The skill uses standard
Read,Write, andEdittools to process metrics and generate test plans. - Sanitization: Not explicitly implemented, as the skill functions as an instructional template for the agent.
Audit Metadata