agent-platform-deploy

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses gcloud and curl to interact with Google Cloud Platform APIs. These commands are fundamental to the skill's purpose of deploying and managing models.
  • [PRIVILEGE_ESCALATION]: The skill includes instructions to modify IAM policy bindings (gcloud projects add-iam-policy-binding) to grant service agents the necessary roles for cross-project model copying. The instructions correctly mandate user confirmation for these sensitive operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input, such as user-defined prompt strings and model IDs, which are interpolated into curl payloads and gcloud commands. While this presents an attack surface, the skill includes explicit safety tiers and confirmation requirements to mitigate risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:40 AM
Security Audit — agent-trust-hub — agent-platform-deploy