ClawHub
Back to skill

Security audit

sql-pro

Security checks across malware telemetry and agentic risk

Overview

This appears to be a database-focused advisory skill with one scope-clarity issue, but no evidence of hidden execution, persistence, credential use, data exfiltration, or destructive behavior.

Reasonable to install if you want SQL or database performance guidance. Invoke it only for clearly database-related tasks, and avoid giving it credentials, private customer data, or production database contents unless you have reviewed and approved that context.

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
94% confidence
Finding
The skill's activation guidance is broad and lacks explicit trigger phrases, exclusions, or scope boundaries, which can cause it to activate for loosely related database or coding tasks. In an agent ecosystem, ambiguous invocation increases the chance of unintended delegation, exposing database context, schema details, or allowing the skill to influence actions in workflows where SQL-specific behavior was not intended.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal