agent-platform-endpoint-management

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides procedural knowledge for using standard Google Cloud CLI commands (gcloud ai endpoints). It identifies and enforces safety tiers, specifically requiring interactive user confirmation for creation/updates (Tier M) and explicit typed confirmation for deletions (Tier D). No malicious patterns such as data exfiltration, prompt injection, or obfuscation were detected. The environment setup steps correctly use standard authentication methods without exposing secrets or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:03 AM
Security Audit — agent-trust-hub — agent-platform-endpoint-management