ClawHub

grafana-insepction

Security checks across malware telemetry and agentic risk

Overview

This skill appears to perform user-started Grafana API inspection and local report generation, with documentation gaps but no evidence of hidden or harmful behavior.

Use a dedicated Viewer-scoped Grafana API key, verify the Grafana URL before running, and keep generated reports private because they can reveal internal monitoring details. Expect API inspection only unless the publisher adds real browser screenshot support.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill documentation describes capabilities that imply network access, reading configuration files, and writing screenshots/reports, but it declares no permissions. That creates a trust and review gap: operators may approve or run the skill without understanding that it can access Grafana endpoints and handle sensitive local files such as API-key-bearing configs. In a Grafana inspection context, this is more dangerous because the workflow explicitly involves authenticated access to monitoring infrastructure and local artifact generation.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding
The skill claims browser screenshot support, but the documented behavior appears limited to API-based inspection and report generation. This mismatch can mislead users about what the skill actually does, which is a security problem when users rely on advertised behavior to assess permissions, execution paths, and data exposure. In this context, inflated or inaccurate claims around inspection features reduce operator ability to review risk accurately.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal