ClawHub

MYSQL QUERY

Security checks across malware telemetry and agentic risk

Overview

This skill is a legitimate database helper, but it gives an agent broad SQL and credential-backed database access without enough guardrails.

Install only if you are comfortable letting an agent run SQL against the databases you configure. Use read-only or least-privilege database users by default, use exact database names, keep production and test credentials clearly separated, prefer SSH keys, and manually review any non-SELECT query before execution.

SkillSpector

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

Vague Triggers

Medium
Confidence
94% confidence
Finding
Database selection by case-insensitive partial name matching is unsafe because an ambiguous or attacker-influenced prompt can resolve to the wrong configured database. In this skill, that could cause SQL intended for a test system to run against production, potentially exposing, modifying, or deleting sensitive data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The usage guidance shows arbitrary SQL execution without a prominent warning that queries may be destructive. In an agent skill, lack of this warning increases the chance that users or higher-level agents treat the tool as read-only and accidentally run UPDATE, DELETE, DROP, or other state-changing statements against real databases.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal