ClawHub
Back to skill

Security audit

废弃mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Chinese-language guide for handling deprecated project content and does not contain executable code or hidden high-impact behavior.

Install this if you want a Chinese-language workflow for reviewing deprecated or legacy content. Before allowing edits, give the agent a clear scope and confirm any deletion or replacement steps, since the skill is designed to advise first and modify only on explicit request.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly mandates Chinese-only output regardless of the user's preference, which overrides normal user-directed behavior and can reduce transparency or usability for users expecting another language. While this is not a code-execution issue, it is a real policy and interaction-layer weakness because hardcoded language constraints can mislead users, impede review, or cause the agent to ignore user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.