Convert natural language requirements (PRD) into AI-friendly DDD domain design documents in Markdown. Use when the user provides a PRD, requirement doc, or business description and wants a DDD domain model, entity/aggregate design, ER diagram, domain logic placement, or sequence/flow diagrams. Produces structured output that AI agents can directly use for implementation.

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 4:20 AM UTC
• Version: 1.0.0

Overview

This skill is a Markdown-only DDD design helper whose behavior matches its stated purpose and shows no evidence of hidden execution, exfiltration, persistence, or privilege abuse.

Install this if you want agents to produce DDD design documents from requirements. Review the generated docs/design file before using it for implementation, and be aware that the default output mixes Chinese business descriptions with English technical names.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Direct Prompt Extraction

High

• Category: System Prompt Leakage
• Confidence: 85% confidence

Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md

| File | Role | When to Read |
|------|------|-------------|
| **This file (SKILL.md)** | Map — workflow, phases, output rules | Always (auto-loaded) |
| [phase-guide.md](phase-guide.md) | How-to — analysis heuristics, design criteria, identification rules | When executing each phase |
| [ddd-design-template.md](ddd-design-template.md) | Template — output section structure with table formats | When writing the design doc |

Direct Prompt Extraction

High

• Category: System Prompt Leakage
• Confidence: 85% confidence

Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md

---

## Output Rules

- Pure Markdown with Mermaid diagrams
- Chinese for business descriptions, English for technical terms (class names, method signatures)

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill description is broadly worded and can activate on many generic requirement-analysis or design requests, increasing the chance the agent invokes it when the user did not specifically ask for DDD transformation. Over-broad routing is risky because it can override user intent, force unnecessary file reads/workflows, and expose internal prompt structure to downstream outputs or reasoning.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The 'When to Use' guidance is ambiguous and lacks clear boundaries, so ordinary requests like general design help or vague 'model this requirement' prompts may incorrectly trigger the skill. This increases the likelihood of inappropriate tool selection and unintended application of a rigid workflow to unrelated tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The output rule forces Chinese for business descriptions and English for technical terms without checking the user's language or formatting preference. This can cause instruction conflict, degrade usability, and produce outputs that do not align with user requirements or system-wide localization expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This markdown template contains substantial bilingual instructions and labels, with many sections presented in Chinese while others are in English. Because the file does not state that it is intended specifically for Chinese-speaking users or offer an opt-in language choice, it can violate a language/locale policy that prohibits forcing a specific language without user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

Line L108 hardcodes a Chinese sentence for the ER diagram note. This imposes a specific language in the skill guidance without offering a language/locale option or explaining a region-specific requirement, which matches the language policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.