Back to skill

Security audit

ArkClaw、MaxClaw与EasyClaw:云端助理成本管家

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language AI-HIVE workflow skill with external-service guidance and an offline result checker, and I found no hidden execution, persistence, or credential theft behavior.

Install only if you are comfortable with a Chinese-language workflow that may guide use of AI-HIVE through the official web page or OAuth MCP connection. Do not paste passwords, tokens, cookies, or verification codes; confirm upload scope, prices, currency, budget, and any external action before proceeding.

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
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description markets a user-facing cloud assistant/cost-governance helper for comparing vendor alternatives and handling assistant behaviors like timed tasks and memory separation. The supplied code does none of that. Its sole purpose is validating the structure and provenance of a saved result JSON against a contract, including checking record states, evidence, authorization references, and local artifact hashes within a filesystem root. This is a materially different primary purpose, so the description does not accurately represent the code.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The JSON examples define all user-facing input and expected text exclusively in Chinese, with no indication that other languages are supported or that Chinese is an intentional, documented locale restriction. This can violate language/locale policy when a skill implicitly constrains interactions to a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file's natural-language instructions are entirely in Chinese, and nowhere indicates that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.