ClawHub
Back to skill

Security audit

SBTI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese joke personality-test skill made of static Markdown quiz content, with no code execution, credential access, persistence, or hidden data flow.

Install this if you want a Chinese-language parody personality quiz. Be aware it may activate on fairly general personality-test wording, and the results are intentionally humorous rather than scientific.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · references/types.md (reported line 60)May include surrounding context.

md
### 纯S — 海豚 (Dolphin)
代号: SS
社交界的天花板，跟谁都能聊到起飞。朋友遍天下，但有多少是真朋友不重要，重要的是热闹。特征：聚会的核心，never say no，手机通讯录2000+且都备注了emoji。

### 纯E — 水母 (Jellyfish)
代号: EE

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad trigger phrases such as '人格测试', '性格测试', '测一测', and '做个测试', which can easily match ordinary conversation and cause unintended activation. While not directly enabling code execution or data exfiltration, overbroad activation can hijack unrelated user interactions, degrade routing quality, and make the assistant behave unexpectedly in benign contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction “中文提问，中文结果” mandates a specific language for interaction and output. There is no indication that the user can opt into another language or that the Chinese-only requirement is justified by a region-specific purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.