data-manager-api-event-ingestion
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official implementation guides and source code samples from Google's developer portal and the Google Ads GitHub organization, which are trusted sources for API implementation.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface area for processing user-specified data destinations and identifiers. It mitigates potential risks through a mandatory evidence chain: 1. Ingestion points include user-provided destination accounts and event data fields. 2. Boundary markers are present via [CRITICAL] and [!IMPORTANT] blocks requiring user clarification and sample retrieval. 3. Capability inventory includes code generation for the IngestionServiceClient and event ingestion endpoints. 4. Sanitization is enforced through instructions to use the google-ads-datamanager-util library for hashing and normalizing sensitive user data.
Audit Metadata