xinjianxue-skill-roommate-global

• Outcome: Pass
• Latest audit: Sep 14, 2026 · 3:52 PM UTC
• Version: 1.0.1

Overview

This skill is a disclosed roommate-advice API integration that asks for consent before analysis and does not include executable code or hidden persistence.

Before installing, understand that using this skill sends birth, gender, and location details to XinJianXue and can consume account tokens. Only provide the one-time authorization code when you intended to bind this AI to your account, and ensure credentials are stored in an OS keychain, credential manager, or other agreed secure location.

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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Anti-Refusal Statement

High

• Category: Anti-Refusal

Content

## 🎯 This Advisor's Positioning (Roommate Relations Advisor)

**In one line**: Do not judge whose living habits are right; deal only with negotiating boundaries.

**Questions handled most often**:
- My roommate is too loud — how do I bring it up?

• Confidence: 85% confidence
• Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Anti-Refusal Statement

High

• Category: Anti-Refusal

Content

## 🎯 This Advisor's Positioning (Roommate Relations Advisor)

**In one line**: Do not judge whose living habits are right; deal only with negotiating boundaries.

**Questions handled most often**:
- My roommate is too loud — how do I bring it up?

• Confidence: 85% confidence
• Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Anti-Refusal Statement

High

• Category: Anti-Refusal

Content

- **Self-check**: Do not judge living habits as right or wrong, better or worse — deal only with negotiating boundaries

• Confidence: 85% confidence
• Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

Call `POST /api/xinjianxue/ai/license/verify` (include credentials if you have them; body or headers are both accepted). **The only criterion is `pass`:**

- `pass: true` → **already onboarded**: use the APIs directly, and do not ask the user for any credential.
- No credentials / `pass: false` → act on the returned `msg`; **go to Step 1 only once you have confirmed "never onboarded"**. Do not blindly re-apply (re-applying produces an extra license that nobody uses).

### Step 1: Apply for the AI business license (once only)

• Confidence: 80% confidence
• Finding: The skill directs the agent to make onboarding state decisions and proceed with account-linked API actions based on a service response, including applying for a license and using stored credentials without renewed user confirmation. In a sensitive workflow involving authentication, billing, and personal data transmission, this increases the risk of unintended external actions or privacy-impacting calls being taken autonomously.

Static analysis

No suspicious patterns detected.