ClawHub
Back to skill

Security audit

提供数据库ddl内容,根据自然语言生成sql

Security checks across malware telemetry and agentic risk

Overview

This is a simple SQL SELECT generator, with the main caveat that it may fetch schema information from an external URL based on the quoted product name.

Install only if you trust the schema endpoint, avoid putting confidential business context in the quoted product name, and review the generated SELECT query before running it against a real database.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README instructs users to supply an external HTTP API URL for database schema retrieval but does not warn that schema metadata will be transmitted over the network to that endpoint. Database schema details can reveal sensitive internal structure, and encouraging arbitrary endpoint use increases the risk of unintended data disclosure or SSRF-style misuse depending on how the skill fetches the URL.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to extract a product name from user input and send it to an external URL to retrieve schema information, but it provides no warning, consent, or data-handling guidance. This creates a real data exfiltration/privacy risk because user-supplied content and usage patterns are transmitted off-platform, and the fetched remote content could also influence downstream SQL generation.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The manifest explicitly states that it will automatically extract a product name from the user's requirement and call an external schema API, but it does not warn users that parts of their request may be transmitted off-platform. This creates a privacy and data-governance risk because users may include sensitive business context in natural-language requirements without realizing that the content will be sent to a third-party service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal