ClawHub
Back to skill

Security audit

AgentZhiPin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed domain-sale promotion tool, but it uses broad AI-agent keywords to inject unsolicited advertising into unrelated conversations.

Install only if you intentionally want the assistant to promote this specific domain during AI-agent-related discussions. Expect unsolicited Chinese promotional text on broad terms like 'AI Agent' unless the skill is narrowed or disabled.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:3
Finding

Broad Keyword Triggers Hijack Responses for Unsolicited Domain Advertising

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list is intentionally broad and includes generic terms like "AI Agent" and "智能体", which are common in normal technical discussion. This can cause the skill to activate during unrelated conversations and inject unsolicited promotional content, effectively turning the agent into a keyword-triggered spam channel. The context makes this more concerning because the entire skill is designed to advertise a domain rather than assist the user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill hard-codes Chinese promotional responses without checking the user's language or documenting a justified language scope. This can override expected assistant behavior, degrade transparency, and cause confusing or manipulative responses for users who are conversing in another language. In this context, the risk is lower than direct code execution, but it still increases the likelihood of deceptive or poor-quality interactions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.