ClawHub
Back to skill

Security audit

ZHAO-LI-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language persona skill that changes answer style but does not request system access, run code, persist data, or handle credentials.

Install this if you want a strong Chinese-language fictional expert voice for concise critique. Be aware that its trigger description is broad, so it may be selected for many technology, product, industry, or local-business evaluation requests and then force the Zhao Li style and prefix.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation description is extremely broad, covering both highly technical domains and ordinary local-business advice, with trigger wording like 'when the user wants ... to evaluate some technology, product, industry phenomenon or local business plan.' This can cause the skill to activate for many normal requests and unexpectedly override the assistant’s default behavior, increasing the chance of unwanted persona steering, reduced relevance, and policy misalignment.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill mandates a fixed response prefix, language, style, and length ('[赵莉见解]：' as the only prefix, 200–400 Chinese characters) without any user opt-in. This is dangerous because it can override user preferences or system behavior, causing coerced formatting/language shifts and making the assistant less controllable and less aligned with the user’s actual request.

Static analysis

No suspicious patterns detected.