ClawHub
Back to skill

Security audit

SQL Cheatsheet

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown SQL reference sheet with some risky SQL examples, but it does not execute code, request credentials, persist behavior, or hide unrelated actions.

Use this as a syntax reference only. Be careful copying modification or schema examples into real databases, especially UPDATE without WHERE, DELETE, TRUNCATE, DROP, and ALTER statements; verify targets, use backups or transactions where appropriate, and test outside production first.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says to use the skill whenever 'needing quick reference for SQL queries, database operations, or common query patterns,' which is a very broad invocation scope rather than a specific trigger or constrained context. In a manifest/markdown description, this can cause unintended activation for many ordinary database-related requests because it does not define clear boundaries or exclusions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The cheatsheet includes destructive operations such as UPDATE without WHERE, DELETE FROM table, TRUNCATE TABLE, and DROP TABLE without prominent safety guidance. In an agent setting, users may copy or adapt these examples into production contexts, increasing the risk of accidental data loss or service disruption.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.