kubesense-alerts
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructs the agent to generate JSON payloads intended for manual import by the user into a UI, ensuring human-in-the-loop oversight before any configuration changes are applied.
- [SAFE]: Data discovery is performed through authorized MCP tools (e.g.,
get-available-metrics,get-trace-or-log-fields) or by referencing internal platform API endpoints, which is standard for platform-specific assistants. - [SAFE]: No obfuscation, persistence mechanisms, or unauthorized network operations were found. The skill maintains a clear, documented purpose for alert rule generation and migration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (Datadog monitor JSON). However, the risk is mitigated by the structured JSON output format and the mandatory manual review step in the Alerts UI before rule creation.
Audit Metadata