ClawHub
Back to skill

Security audit

Grafana

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Grafana integration that uses ClawLink credentials to inspect and manage Grafana resources, with write actions explicitly requiring user confirmation.

Install this only if you want ClawLink-connected OpenClaw access to your Grafana environment. Use a least-privilege Grafana API key or service account, review write previews carefully, and avoid granting Grafana admin-level credentials unless the agent truly needs to manage data sources, teams, permissions, or alerts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description is broadly phrased around querying observability data and managing Grafana resources, which can cause the skill to activate for many generic monitoring-related requests. Over-broad activation increases the chance the agent invokes a capability-bearing integration unnecessarily, exposing sensitive monitoring metadata or enabling unintended write-paths if later prompts steer toward modification actions.

Vague Triggers

Low
Confidence
84% confidence
Finding
The guidance explains what the skill can do but does not define strong trigger boundaries or negative examples for when it should not run. In an agent environment, this ambiguity can lead to accidental invocation on loosely related requests, which widens access to connected Grafana data and increases the attack surface for prompt steering.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.