gke-golden-path

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to accept various user-defined inputs which are subsequently utilized as arguments for cluster creation and update tools. • Ingestion points: Required inputs such as Project ID, Region, and Cluster name are collected directly from the user (found in SKILL.md). • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat user input as data rather than instructions. • Capability inventory: The skill leverages high-privilege MCP tools like create_cluster and update_cluster to modify cloud infrastructure (found in SKILL.md). • Sanitization: The instructions do not define any validation or sanitization routines for the user-supplied strings before they are passed to the underlying tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 AM
Security Audit — agent-trust-hub — gke-golden-path