ClawHub
Back to skill

Security audit

Ops Dashboard

Security checks across malware telemetry and agentic risk

Overview

This skill is a local operations dashboard that reads workspace and git health metadata, with no evidence of network sharing, persistence, credential access, or destructive behavior.

Install only if you are comfortable with the agent seeing local workspace health details, including git status, recent commit summaries, changed file paths, directory names and sizes, disk usage, and system load. Avoid pointing `--workspace` at repositories where that metadata should remain private.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill describes and exposes functionality that reads workspace files and invokes shell-backed system and git inspection commands, but it does not declare any permissions. This creates a transparency and policy-enforcement gap: consumers may run a skill with broader filesystem and command-execution reach than advertised, increasing the chance of unauthorized data exposure or unsafe execution in sensitive environments.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.