adk-deploy-guide
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The guide describes architectural patterns for event-driven agent invocations in
references/event-driven.md. These patterns involve processing external untrusted data (Pub/Sub, Eventarc, BigQuery) as agent input, which presents a surface for indirect prompt injection.\n - Ingestion points:
references/event-driven.mddefines FastAPI endpoints for Pub/Sub, Eventarc, and BigQuery Remote Functions.\n - Boundary markers: The provided Python code examples do not include explicit delimiters or 'ignore' instructions for the incoming message payloads.\n
- Capability inventory: The skill leverages high-privilege capabilities including infrastructure deployment via
terraform apply, cloud resource management throughgcloud, and CI/CD operations viagh auth.\n - Sanitization: The implementation patterns demonstrate direct injection of external payloads into the agent runner without explicit sanitization or validation logic.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration files from
google.github.io(a well-known service) and utilizes theuvxtool to execute theagent-starter-packutility.\n- [COMMAND_EXECUTION]: The documentation provides instructions for executing essential deployment commands such asmake deploy,adk deploy,terraform apply, andgh auth loginas part of the standard production workflow.
Audit Metadata