Security audit

Data Model Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a construction data-modeling helper with disclosed SQL and schema generation, but its generated SQL should be reviewed before use.

Install only if you are comfortable reviewing generated database schemas before applying them. Treat SQL output as a draft, use it primarily for MySQL unless modified, and do not feed untrusted project data into schema generation without validating identifiers, comments, and default values first.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:178
Finding: Unsanitized Model Data Produces Injectable SQL DDL
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description and heading content are entirely in Chinese and explicitly position the tool for Chinese construction projects, but they do not state whether Chinese is required or optional, nor do they offer any user language choice. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: generate_sql_schema(self, dialect: str = "mysql") suggests the function will vary output by dialect, and the surrounding documentation presents multiple supported databases. In reality, the function never branches on dialect and always renders the same MySQL-oriented schema, creating an active mismatch between stated intent and actual behavior.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The documentation states support for MySQL, PostgreSQL, SQL Server, and SQLite, and the API accepts a dialect parameter. However, generate_sql_schema ignores the dialect argument and emits MySQL-specific syntax such as backtick quoting, ENGINE=InnoDB, DEFAULT CHARSET=utf8mb4, and COMMENT, which do not match the claimed broader database-generation behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.