gke-observability

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates for executing gcloud and kubectl commands to modify cluster configurations and query logs.
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes tools that ingest data from external, potentially untrusted sources.
  • Ingestion points: The tools gke:get_k8s_logs and gke:list_k8s_events (referenced in SKILL.md) allow the agent to read data from the Kubernetes cluster environment.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the log/event data.
  • Capability inventory: The skill enables high-privilege operations such as cluster updates via gcloud container clusters update and log retrieval via gcloud logging read.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from cluster logs or events before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 AM
Security Audit — agent-trust-hub — gke-observability