openai-ads
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill's instructions are consistent with its purpose and include safety protocols such as manual activation of entities and use of idempotency keys.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from ad account insights and user-provided ad copy. 1. Ingestion points: account cache (openai_ads_caches_get), campaign and audience lists, and user-provided text/URLs. 2. Boundary markers: No specific delimiters are mandated in the instructions for tool output. 3. Capability inventory: Creation, update, and activation of campaigns, ad groups, and ads via API tools. 4. Sanitization: Not explicitly documented; relies on the underlying platform and API validation.
Audit Metadata