ClawHub

zeh-local-inspector

Security checks across malware telemetry and agentic risk

Overview

This is a small read-only local directory inspector that reports the current folder and a short list of entry names.

Install only if you are comfortable with the agent revealing the current folder path and a small top-level directory listing. Use it in directories where that metadata is acceptable, and review updates before enabling future versions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to run a local inspection script that necessarily reads from the working directory, but the manifest does not declare any corresponding file-read permission. This creates a transparency and policy-enforcement gap: reviewers and permission systems cannot accurately assess or constrain what the skill can access locally.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation condition, 'when the user asks to inspect the local environment in a safe and minimal way,' is vague and broad, which can cause the skill to activate for loosely related requests. In a local-inspection skill, over-broad triggering increases the chance of unnecessary filesystem access and disclosure of sensitive workspace information.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal