agent-platform-inference

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill adheres to security best practices for Google Cloud authentication by leveraging Application Default Credentials (ADC), ensuring no sensitive API keys or service account JSONs are hardcoded.
  • [SAFE]: Dependencies listed in requirements.txt (google-genai, google-cloud-aiplatform, openai, google-auth) are official, widely-used libraries from trusted sources.
  • [SAFE]: All external documentation and model reference links target trusted Google Cloud domains.
  • [COMMAND_EXECUTION]: Includes a utility script (scripts/verify_all.sh) designed to test the local python examples; this execution is confined to the skill's own local environment and serves a legitimate developmental purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:03 AM
Security Audit — agent-trust-hub — agent-platform-inference