ClawHub
Back to skill

Security audit

SQL全生命周期审核

Security checks across malware telemetry and agentic risk

Overview

This is a SQL auditing helper with no bundled executable code, but users should confirm the target database and any SQL file before use.

Install only if you intend to use the local dbskiter tool for SQL auditing. Before running it, confirm the intended database/environment, review any SQL or DDL being analyzed, and avoid pointing it at production-sensitive files unless authorized.

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
80% confidence
Finding
The trigger phrases are broad enough that an agent may invoke the skill in contexts where the user did not explicitly consent to database-related analysis. In this skill's context, unintended invocation matters because commands can inspect SQL, DDL, or files tied to a real database, increasing the risk of exposing sensitive schema/query information or causing analysis against the wrong target.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill does not clearly warn that commands operate against a specified database and may process SQL files or DDL from user systems. In a database-auditing context, missing this disclosure can lead users or agents to submit production queries, schema definitions, or local file paths without understanding the sensitivity of that data.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.