ClawHub
Back to skill

Security audit

【官方】知识星球·星球管理工具

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only guide for using zsxq-cli to view Knowledge Planet groups, topics, tags, and member search results from the user's own logged-in account.

Installers should treat JSON output from this skill as potentially sensitive because it may include more group, owner, statistics, topic, or hashtag metadata than the table view; share or store those outputs only when appropriate for the logged-in zsxq account.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The markdown explicitly recommends --json output and notes it includes full fields such as owner and statistics, but it does not warn that this may reveal additional account or group metadata beyond the simple table view. Because this skill describes behavior that could affect privacy or data handling, a brief disclosure would improve user awareness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.