infrastructure
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes instructions for running system and cluster commands, such as
kubectlfor resource management,helmfor package installation, andsystemctlfor service control. These are required for the intended purpose of configuring monitoring components. - [EXTERNAL_DOWNLOADS]: The skill references and downloads Helm charts from Grafana's official repository at
https://grafana.github.io/helm-charts. These downloads are from a trusted infrastructure provider associated with the skill author. - [CREDENTIALS_UNSAFE]: The file
references/clouds-and-hosts.mdcontains hardcoded AWS access keys (AKIAIOSFODNN7EXAMPLE). Although these are well-known documentation placeholders, they match patterns for hardcoded secrets. - [DATA_EXFILTRATION]: The skill is designed to ship cluster and host telemetry (metrics, logs, and traces) to external Grafana Cloud endpoints (e.g.,
*.grafana.net). This is the primary legitimate function of the infrastructure monitoring skill.
Audit Metadata