ClawHub
Back to skill

Security audit

Database Helper Pro

Security checks across malware telemetry and agentic risk

Overview

This database skill appears useful but asks for broad SQL/database authority without clear safety boundaries for write or destructive operations.

Review before installing. Use this only with a restricted database account, preferably read-only unless you explicitly need writes. Require explicit confirmation before CREATE, UPDATE, DELETE, DROP, import/export, or schema changes, and avoid connecting it to production data without backups and rollback procedures.

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
92% confidence
Finding
The activation phrase set is overly broad, including generic terms like 'SQL', 'database', and '查询', which are likely to appear in normal user conversations. That makes accidental invocation more likely, and because this skill exposes database querying and modification capabilities, unintended activation could trigger sensitive or destructive actions in the wrong context.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises destructive capabilities such as schema creation/modification and SQL data operations without any warning, safety boundary, or confirmation requirement. In context, this is more dangerous because the implementation includes direct execution of arbitrary queries and table/CSV operations, so a user or downstream agent could unintentionally modify or destroy data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.