ClawHub
Back to skill

Security audit

ZeeLin AI头部简讯

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese AI-news briefing skill that uses web searches to gather public information and does not include code, install hooks, credential access, or destructive behavior.

Install this if you want Chinese AI news digests sourced from public web results. Be aware that it will perform current web searches and may default to Chinese output; ask for a specific language or narrower topic if needed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description includes broad trigger phrases like 'AI周报' and '本周AI有什么新进展', which can overlap with ordinary user requests and cause unintended invocation. Over-broad activation can route unrelated or general requests into this skill, leading to context capture, tool use, or output shaping the user did not explicitly intend.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Generic mode triggers such as '日报', '快讯', and '周报' are common across many non-AI contexts and make the skill's invocation boundary ambiguous. This increases the chance of accidental activation and inappropriate web-search behavior in response to generic reporting requests that were meant for another topic or tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The note '中文输出为主' sets a language policy for all summaries and analysis, but the file does not offer the user a choice of language or describe this as an opt-in preference. This can violate language or locale policy requirements when a skill forces a specific language by default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.