xinjianxue-skill-marriage_match-global

• Outcome: Review
• Latest audit: Sep 14, 2026 · 3:38 PM UTC
• Version: 1.0.1

Overview

The skill is coherent for a paid XinJianXue relationship-analysis API, but it asks users to enter a sensitive one-time account authorization code in chat and sends detailed personal profile data to an external service.

Review this carefully before installing. Only use it if you are comfortable sending the authorization code through the AI chat, binding the AI to your XinJianXue account, storing generated credentials locally, spending service tokens per report, and transmitting birth and location details to www.xinjianxue.com. Do not submit information about another person unless they have agreed.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• 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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

• Location: SKILL.md:131

Finding

Sensitive One-Time Authorization Code Collected Through Conversation Context

Content

View full analysis

"Open the official website **www.xinjianxue.com → sign in → "Personal Center" (个人中心) → "AI Assistant Authorization Code" (AI 助手授权码)**, and send me the 8-character authorization code shown there; I need it to complete the account binding. > Reminder: this code is a **sensitive one-time credential** that is voided the moment the binding succeeds — please confirm you are talking to the official XinJianXue AI assistant (service domain `www.xinjianxue.com`) and send it only to me, this one AI; do not post it in a group chat, do not screenshot or share it, and do not give it to any other AI." `POST /api/xinjianxue/ai/license/bind` with body: ```json { "license": "XJX-AI-xxxxxxxxxxxxxxxx", "auth_code": "" } ``` ``` ### Technical Analysis The Skill explicitly classifies the authorization code as a sensitive, one-time credential but requires the user to submit it directly through the AI conversation. This places the secret in model context and potentially in conversation history, application telemetry, diagnostic traces, or platform logs. Although successful binding invalidates the code, there is an exposure window between disclosure and binding. Any party able to access the live conversation or retained logs during that window may recover the code. The binding operation is security-sensitive because it associates an AI-controlled license with the user's external service account and returns ...[truncated 1551 chars]

Remediation

View remediation

other

Warning

• Location: SKILL.md:203

Finding

Broad Personal and Location Data Required for External Processing

Content

View full analysis

⚠️ **Before you start**: calling this service sends personal information about the subject — date of birth (plus time, if known), gender, place of birth, current location — to the XinJianXue API (`www.xinjianxue.com`) for processing; it is used only for this one analysis and is not stored. This AI calls under your account identity and consumes tokens per call. **Please confirm you understand and agree before starting.** ``` ### Technical Analysis The Skill requires a combination of date of birth, gender, and current city-level location for even the basic report. The full tier additionally collects exact birth time and place of birth. Multi-person requests may also include names and equivalent attributes for several people. These combined attributes can be identifying or highly linkable, particularly whe ...[truncated 2156 chars]

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 80% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md

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)

Static analysis

No suspicious patterns detected.