Back to skill

Security audit

私人助理代接业务助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language business-reception assistant with guarded external-tool guidance and no evidence of hidden execution, persistence, credential capture, or destructive behavior.

Before installing, confirm you are comfortable with a Chinese-language workflow and with optionally connecting AI-HIVE through the official OAuth/MCP path. Do not provide credentials in chat, review any upload scope and paid budget first, and require separate explicit approval for sending messages, payments, refunds, deletions, publishing, or business-system changes.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose is business reception assistance, but the skill also instructs use of a local validation script that checks files, paths, hashes, and possible credential strings. That hidden operational behavior expands the trust boundary into local artifact inspection and compliance checking, which can expose sensitive local data or perform unintended analysis beyond what the description promises.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill references local files and an offline validation script, which implies file-read capability, but it does not declare any explicit tool scope or permissions. This creates an authorization-boundary mismatch: a host may allow broader file access than users expect, and reviewers cannot easily determine what filesystem access is intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The user-facing description and instructions are entirely in Chinese, and there is no statement that the skill can operate in other languages or that Chinese is optional. This creates a natural-language locale constraint without explicit user choice or documented justification as a region-specific tool.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The interface text broadens the skill from a business-reception knowledge-card assistant into something that appears to deliver task artifacts, evidence, and connect external verification tooling. This mismatch can mislead an orchestrator or user into granting broader trust, permissions, or workflows than the skill’s stated purpose justifies, increasing the chance of unauthorized data handling or unintended tool use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains all user-facing instructions in Chinese and does not indicate that users can opt into another language or locale. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The only user-facing guidance in this file is written in Chinese: "空值供用户按实际任务填写,不填密码、Token、验证码、Cookie或完整证件信息。" For a general intake manifest with no stated regional or locale restriction, this creates a language-policy concern because it assumes a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.