adk-observability-guide

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation hosted on Google's GitHub Pages (google.github.io) and describes using uvx to run the agent-starter-pack scaffolding utility. These references target trusted organizational resources and standard developer tools.- [COMMAND_EXECUTION]: Provides a set of verification commands using standard Cloud SDK tools (gcloud, gsutil, bq) to confirm that telemetry and logging infrastructure are functioning correctly in the user's environment.- [DATA_EXFILTRATION]: Describes the configuration of prompt-response logging to Google Cloud Storage and BigQuery. This is the primary purpose of the observability skill and includes specific instructions on using privacy-preserving modes (such as NO_CONTENT) to minimize the capture of sensitive interaction data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:53 PM
Security Audit — agent-trust-hub — adk-observability-guide