rpe-grafana

• Outcome: Pass
• Latest audit: May 28, 2026 at 6:01 AM UTC
• Version:
  1.0.2

Overview

This is a disclosed read-only Grafana integration, but users should treat returned dashboard metrics as potentially sensitive.

Install only with a trusted Grafana URL and a least-privileged Viewer or read-only service account. Do not provide admin credentials or access to dashboards the agent should not be allowed to read, because this skill can retrieve values from any visible dashboard and panel.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The documentation explains that the skill executes existing panel queries through Grafana's datasource API using supplied credentials, but it does not clearly warn that dashboard requests, query definitions, and returned metric values may contain sensitive operational or business data. Users may invoke the skill without understanding that it transmits and retrieves potentially sensitive information from Grafana-backed datasources.

VirusTotal

65/65 vendors flagged this skill as clean.