Security audit

ym-sql-change-precheck

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only SQL change review skill that is clearly scoped to static pre-deployment risk analysis and does not show hidden execution, network use, or persistence.

Install this if you want a Chinese-language assistant workflow for reviewing SQL change scripts before deployment. Treat its generated rollback SQL and rewrite suggestions as review aids only; the skill itself also says DBA or human approval is still required before running anything.

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 (3)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The description includes broad activation phrases such as “数据库变更” and “sql review”, which can match many ordinary database discussions that are not specifically asking for a precheck. Over-broad triggers can cause the skill to activate unexpectedly, intercept unrelated prompts, and steer the agent into an unintended workflow, reducing reliability and potentially exposing user SQL or operational context unnecessarily.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The manifest trigger list contains ambiguous broad phrases, especially “数据库变更” and “sql review”, without constraints that the user must be asking for release/pre-execution safety review. In an agent routing system, this increases unintended invocation risk and can cause misrouting away from more appropriate skills, which is a genuine security and safety concern when skills process sensitive operational scripts.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all guidance exclusively in Chinese and does not offer an opt-in language choice or document a justified locale restriction, which may conflict with organizational language-choice requirements.

Static analysis

No suspicious patterns detected.