ClawHub
Back to skill

Security audit

Text To Sql

Security checks across malware telemetry and agentic risk

Overview

This is a plain text-to-SQL helper that writes queries from user-provided schemas and does not show hidden execution, data collection, or persistence.

Safe to install as a SQL-writing aid. Users should still review generated SQL before running it, especially against production databases or sensitive business data, because the skill generates queries but does not verify database permissions or execution impact.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The front-matter says to use the skill when a user asks for SQL, including generic requests like 'write SQL for this,' while the body later says activation requires natural language request plus schema plus SQL request. That inconsistency can cause the agent to invoke the skill without schema context, increasing the chance it invents tables or columns and produces misleading or unsafe queries that users may execute against real databases.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.