sql-explain

Security checks across malware telemetry and agentic risk

Overview

This is a local SQL helper that formats, analyzes, and drafts SQL text without database access or hidden persistence.

Treat generated SQL as a draft. Review any INSERT, UPDATE, or DELETE carefully before running it on a real database, and prefer the packaged artifact over the optional curl download unless you trust that source.

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: 91% confidence
Finding: The trigger phrases include broad, natural requests such as '分析sql', '这个sql怎么写', and 'explain this query', which are common in normal conversation and can cause accidental or overly broad activation. Unintended invocation can route unrelated user content into this skill, increasing the chance of incorrect handling, privacy issues, or undesired generation of SQL statements.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The NL-to-SQL function generates UPDATE and DELETE statements from natural-language prompts with no warning, confirmation step, or safety guardrails. In an agent context, this can enable unintended destructive queries to be produced and potentially executed downstream, especially because the templates normalize dangerous operations as standard behavior.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal