agent-platform-prompt-management

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFE
Full Analysis
  • Official SDK Integration: The skill facilitates interactions with cloud services through established libraries, specifically google-cloud-aiplatform and google-genai.
  • Authentication Standards: It correctly advises the use of gcloud auth login and Application Default Credentials (ADC), which is the recommended secure approach for local environment authentication.
  • Operational Safety Gates: The inclusion of 'Tier M' and 'Tier D' confirmation requirements ensures that the agent requests explicit user approval before generating code for mutating or destructive actions.
  • Input Management: The skill dynamically populates Python snippets with resource identifiers provided by the user. While this creates a data ingestion surface, it is consistent with the skill's primary function of cloud resource orchestration.
  • Environment Isolation: The recommendation to use a dedicated Python virtual environment for SDK operations aligns with software development best practices for dependency management.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 10:00 PM
Security Audit — agent-trust-hub — agent-platform-prompt-management