dt-obs-kubernetes

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted telemetry data from the monitored Kubernetes environment.
  • Ingestion points: Uses fetch logs and fetch events in SKILL.md and references/pod-debugging.md, and calls the get-events-for-kubernetes-cluster tool.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided in the DQL query snippets.
  • Capability inventory: Extensive read capabilities for infrastructure (Smartscape), metrics (timeseries), and telemetry data (logs, events).
  • Sanitization: No explicit sanitization of log/event content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:09 PM