xinjianxue-skill-friend_qa-global

• Outcome: Pass
• Latest audit: Sep 14, 2026 · 4:20 PM UTC
• Version: 1.0.1

Overview

This skill is a disclosed advisor integration that sends user-approved relationship-analysis inputs to a paid XinJianXue API and stores only the service credentials needed for later calls.

Before installing, understand that this skill uses a third-party paid API, may consume account tokens, and sends personal birth, gender, and location details for each confirmed analysis. Use a dedicated credential store, do not share the one-time authorization code except during binding, and only run analyses for people who have been explicitly agreed to in the conversation.

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 (2)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• 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.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md

**Delivery style**: Give the benign explanation and the time dimension first, then talk about how to handle it.

**What this advisor will not take on**:
- Do not judge one cold spell as "this friendship is over"
- Do not decide for the user to cut the person off

> That is this advisor's sense of direction.

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.