openai-ads
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust safety control by mandating that all new campaigns, ad groups, and ads be created in a 'paused' state. This ensures a human-in-the-loop verification step before any live ad delivery or spending occurs.
- [SAFE]: Authentication and account management are handled through the developer's official platform (Hyper MCP), with credentials managed securely via the application dashboard rather than being hardcoded or requested within the prompts.
- [SAFE]: All network operations are scoped to legitimate service endpoints (api.ads.openai.com) and the vendor's infrastructure (hyperfx-ai.com). No suspicious third-party downloads or remote code execution patterns were identified.
- [SAFE]: No obfuscation, hidden instructions, or attempts to bypass system safety guidelines were found within the skill's markdown instructions or reference documentation.
Audit Metadata