ClawHub
Back to skill

Security audit

个人Agent接入AI-HIVE助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language AI-HIVE onboarding helper with cautious user-authorization checks and no hidden persistence or automatic credential handling found.

Install only if you are comfortable using the AI-HIVE web/MCP service in Chinese. Do not paste secrets into chat, confirm upload scope and budget before any paid or external action, and treat the checker as a local structure/hash validator rather than proof that an AI-HIVE action really succeeded.

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 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
98% confidence
Finding

The skill is presented as an AI-HIVE onboarding and MCP integration helper, but the analyzed behavior appears centered on local file validation and result-record checking rather than the declared integration workflow. This mismatch is dangerous because reviewers and users may grant trust or permissions based on the stated purpose while the skill performs materially different actions, creating room for unintended data access or deceptive operation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill references local artifacts and an offline validation script, which implies file-reading capability, but it does not declare any tool scope or allowed-tools boundary. Missing capability declarations weaken reviewability and can let a skill access local files beyond what users or the platform expect, especially when the skill is treated as documentation-driven behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This JSON file contains all user-facing behavioral examples exclusively in Chinese, with no indication that language selection is optional or constrained to a Chinese-specific deployment. That can violate a language/locale policy when the skill implicitly enforces one language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file’s natural-language instructions are exclusively in Chinese, which effectively forces a specific language for users consuming this skill documentation. The policy allows locale constraints only when they are clearly documented and justified or when users are given a language choice, neither of which appears here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.