data-manager-api-audience-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 several official Google developer guides and sample code repositories on GitHub (e.g., github.com/googleads). These links are provided for developer reference and implementation guidance and originate from well-known and trusted official sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external user data into Google advertising products, creating a potential surface for indirect injection if malicious instructions were embedded in the ingested data.
  • Ingestion points: The process ingests identifiers such as email addresses, phone numbers, and mobile device IDs from user-provided datasets (found in SKILL.md and references/formatting.md).
  • Boundary markers: The skill requires clarification of the destination account and the use of strictly defined API request payloads.
  • Capability inventory: The skill uses network operations to communicate with the IngestionServiceClient and UserListServiceClient APIs.
  • Sanitization: The instructions mandate the use of the google.ads.datamanager_util library to normalize and hash (SHA256) all user identifiers before they are transmitted, which effectively sanitizes the data from being interpreted as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:40 AM
Security Audit — agent-trust-hub — data-manager-api-audience-ingestion