ClawHub
Back to skill

Security audit

File Indexer

Security checks across malware telemetry and agentic risk

Overview

This is a local file-finding skill that indexes disclosed filesystem metadata in limited folders and does not show hidden network, credential, or destructive behavior.

Install only if you are comfortable with a local database of filenames, full paths, sizes, and dates from ~/Documenti and ~/Scaricati. Review those folders before running rebuild or enabling periodic updates, and avoid placing symlinks or sensitive filenames in indexed folders if path privacy matters.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill advertises and instructs use of a script that reads the filesystem and writes a SQLite catalog, but the skill declares no permissions. That mismatch can bypass user/operator expectations and weakens security review because the capability to enumerate files and persist metadata is present even though it is not explicitly declared.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger phrase "where is" is very generic and can match ordinary conversation, causing the skill to activate unexpectedly. In a filesystem-indexing skill, unintended activation can expose file metadata or cause unsolicited searches over local paths, increasing privacy risk even if file contents are not read.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The tool indexes and later prints sensitive filesystem metadata including full absolute paths, filenames, sizes, and modification times. In an agent skill context, this can expose private user information such as document names, project structure, downloads, and other behavioral signals without any explicit consent flow, visibility controls, or output minimization.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.