krea2-megastructure-prompts

• Outcome: Pass
• Latest audit: Sep 14, 2026 · 2:24 AM UTC
• Version: 1.0.0

Overview

This is a Markdown-only Krea 2 prompt helper with no executable behavior; the main caveats are broad activation wording and fixed English/Chinese output defaults.

Install it if you want a Chinese-oriented helper for writing Krea 2 megastructure prompts. Prefer project-level installation if you only want it available in one workspace, and expect generated prompts to default to English with Chinese notes unless you ask otherwise.

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

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Skill Enumeration

Medium

• Category: Agent Snooping

Content

最终路径形如：

```
~/.workbuddy/skills/krea2-megastructure-prompts/SKILL.md
```

复制完成后重启一次会话（或新开一个对话），即可通过描述需求触发。

• Confidence: 80% confidence
• Finding: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The README says the skill can be triggered simply by 'describing your needs,' which is an ambiguous activation condition for a markdown skill description. This broad phrasing does not define what kinds of requests should or should not invoke the skill, increasing the risk of unintended activation during ordinary conversation.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The sample triggers are presented as plain natural requests such as '帮我写一个...' and '给我 3 个...', which are common conversational phrases rather than clearly scoped skill invocations. Because there are no negative examples or activation constraints, these examples may encourage accidental triggering outside the intended Krea 2 prompt-generation context.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The README states that output includes '1 条英文主提示词' because 'Krea 2 is an English model,' which imposes a language choice in the skill's behavior. This is a natural-language policy concern because the documentation does not indicate that users may choose another language format or opt in to English-only output.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger description is excessively broad, matching generic requests about anything "huge," "epic," or "impressive," which can cause the skill to activate outside its intended niche. Overbroad activation can hijack unrelated conversations, override more suitable skills, and produce unwanted prompt-generation behavior that degrades routing integrity and user intent handling.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The skill metadata says output includes English prompts plus Chinese explanation and parameter advice, without indicating adaptation to the user's language. This can override user language preference, leak unexpected language into downstream workflows, and reduce usability or correctness in multilingual contexts where output format matters.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: Line L003 states that every prompt is a complete English long sentence for direct use, which imposes a specific language choice. The file does not offer an alternative language option or indicate that English is optional, so it conflicts with the language/locale choice policy.

Natural-Language Policy Violations

Medium

• Confidence: 98% confidence
• Finding: This markdown skill forces a specific language for its instructions and guidance, and nowhere indicates that the user can opt into Chinese or select another language. Under the stated policy, a language constraint is a natural-language policy issue unless it is optional or clearly justified as region-specific.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The document is written as a Chinese-only skill reference, including headings and instructions, with no indication that users may choose another language or locale. Under the policy rules, forcing a specific language without opt-in is a natural-language policy violation unless clearly justified as region-specific.

Natural-Language Policy Violations

Low

• Confidence: 89% confidence
• Finding: This markdown file contains user-facing guidance exclusively in Chinese, including headings, usage notes, and instructions. Under the language/locale policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no justification or language choice is provided.

Static analysis

No suspicious patterns detected.