ClawHub
Back to skill

Security audit

Db Explorer

Security checks across malware telemetry and agentic risk

Overview

This database helper is mostly a disclosed, purpose-aligned skill, but users should treat its export, backup, restore, and migration examples as sensitive operations.

Install only if you are comfortable giving an agent database connection details. Keep it read-only unless you explicitly request a write, restore, import, or migration; review every command first, use limited database accounts where possible, and store or delete exports/backups according to your data handling rules.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill is presented as an exploration/querying tool, but it also includes restore and migration commands that can modify databases and the filesystem. This mismatch increases the chance an agent or user invokes destructive operations under the assumption the skill is largely read-only, leading to accidental data loss, overwrite, or unauthorized replication of data.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The file states the skill is read-only by default and that write operations require confirmation, but later provides direct restore/import commands with no confirmation pattern or safety wrapper. That inconsistency can cause agents to execute destructive commands without the promised safeguards, creating a real risk of database corruption or overwrite.

Context-Inappropriate Capability

Low
Confidence
84% confidence
Finding
Including backup, restore, and shell-level migration in a database exploration skill expands the skill's authority beyond its stated purpose. Even if administratively useful, these capabilities enable filesystem writes and cross-system data movement that can expose sensitive data or cause unintended operational changes when the skill is activated for routine inspection.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation phrases are broad enough that the skill may trigger on vague requests like checking data or showing a database, even when the user did not intend database-side operations. In a skill that also documents restore, export, and migration actions, overbroad invocation increases the risk of inappropriate tool selection and unnecessary exposure to sensitive systems.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
Export and related operational behaviors are documented as normal workflows without strong user-facing warnings about writing files, handling sensitive data, or potential modification in adjacent backup/restore scenarios. This can result in silent data exfiltration to local storage, insecure handling of exports, or confusion about when commands affect the database versus only the filesystem.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.