conversational-analytics-api

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical guide for developers. It includes code snippets that use the google-cloud-geminidataanalytics library to interact with Google Cloud services.
  • [CREDENTIALS_UNSAFE]: The code snippets include placeholders for authentication (e.g., YOUR_CLIENT_ID, YOUR_CLIENT_SECRET), which is a safe practice for documentation and does not expose actual secrets.
  • [EXTERNAL_DOWNLOADS]: The skill references official Google Cloud APIs (googleapis.com) and standard client libraries, which are well-known and trusted services.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data exfiltration were detected. The network operations are directed at official Google Cloud endpoints for the intended purpose of the skill.
  • [PROMPT_INJECTION]: The skill describes a conversational analytics system which represents a surface for indirect prompt injection. This is the intended behavior of the described service, and the skill provides guidance on improving accuracy through 'Golden Queries' and system instructions.
  • Ingestion points: User questions provided to the ChatRequest (SKILL.md).
  • Boundary markers: Not explicitly defined in the provided code examples.
  • Capability inventory: Querying Looker Explores and performing Python-based data analysis via AnalysisOptions (SKILL.md).
  • Sanitization: The skill recommends using 'Golden Queries' and specific 'System Instructions' to guide agent behavior and improve response accuracy.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 12:22 AM