Back to skill

Security audit

SQL 查询优化助手

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent SQL-help skill made of Markdown guidance, with no hidden execution or persistence, though users should treat database diagnostics and logs carefully.

Installers should expect Chinese-language SQL guidance. Before applying generated SQL, review it for the target database and environment, avoid running mutation or configuration commands blindly in production, and treat slow-query logs as sensitive because they may expose schema details or user-derived values.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill title and all operational guidance are written in Chinese, while the manifest description above is in English, creating an implicit language constraint for users. The file does not offer any opt-in, alternative locale, or explanation that the skill is intended only for a Chinese-language context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The guidance tells users to enable global slow-query logging and set thresholds, but it does not warn that logged SQL may include sensitive literals, schema details, or user-derived values depending on application behavior and database configuration. In a SQL assistant skill, this is a real security/privacy concern because users may apply the instructions directly in production and store sensitive query data in broadly accessible log files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The PostgreSQL full-text search examples hard-code the 'english' dictionary in both index creation and querying. This imposes a specific language/locale behavior in a general database best-practices document without offering alternatives or explaining that the examples are English-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

A language-specific skill document can violate language/locale policy when it forces one language without user opt-in or documented justification. This file presents all instructions exclusively in Chinese and does not indicate that Chinese is optional or region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.