ClawHub

sql-explain

Security checks across malware telemetry and agentic risk

Overview

This is a local SQL helper that formats, analyzes, explains, and generates SQL text without hidden network access, credential use, persistence, or database execution.

Reasonable to install for local SQL formatting and explanation. Treat generated UPDATE or DELETE SQL as drafts, review WHERE clauses carefully, and avoid running generated SQL against production data without manual validation, a transaction, or a backup.

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
90% confidence
Finding
The trigger phrases are broad enough to match many ordinary SQL-help requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. That increases the chance of unintended routing, prompt hijacking surface, or the skill handling requests outside its narrow purpose, especially in environments with multiple overlapping skills.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The nl_to_sql function generates UPDATE and DELETE statements from natural-language prompts without any safety interlock, warning, confirmation step, or restriction to read-only output. In an agent context, this can facilitate unsafe automation or accidental destructive queries, especially because the templates normalize dangerous operations into a one-step generation path that downstream tools or users may execute without sufficient review.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal