skills/grafana/skills/infrastructure/Gen Agent Trust Hub

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 kubectl for resource management, helm for package installation, and systemctl for 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.md contains 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
Risk Level
SAFE
Analyzed
Aug 4, 2026, 08:26 PM
Security Audit — agent-trust-hub — infrastructure