Back to skill

Security audit

Claude Cowork与Copilot Tasks平替:办公任务交付台

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language workflow skill for office task delivery with optional user-authorized AI-HIVE use and clear safeguards around credentials, file changes, uploads, paid actions, and external execution.

Install only if you are comfortable using a Chinese-language office-workflow skill and, if you choose AI-HIVE, authorizing it through the official browser/OAuth flow. Do not paste passwords, tokens, cookies, or verification codes into chat, and require explicit previews and authorization before uploads, paid calls, file modifications, sending, deletion, or public posting.

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
98% confidence
Finding

The skill is marketed as an AI-powered office task delivery assistant with authorized tool integrations, but the provided content only defines process guidance, local artifact handling, and validation steps rather than implementing the claimed capabilities. This mismatch is dangerous because users may rely on the skill for task execution, external actions, or provider-backed functionality that does not actually exist, leading to unsafe assumptions, incorrect delegation, or accidental exposure of sensitive work materials to an unverified workflow.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill references reading local assets and reference files and instructs use of a local validation script, but it declares no explicit tool scope or allowed-tools policy. Missing scope declarations can cause overbroad or ambiguous file access at runtime, weakening least-privilege controls and making it harder to audit what the skill is allowed to read.

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 user-facing operational instructions only in Chinese, which can impose a language constraint on users without opt-in. Under the policy rule, forcing a specific language without offering alternatives or documenting a justified regional scope is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill file is written in Chinese and presents all workflow instructions exclusively in that language, with no indication that language selection is optional or that the skill is limited to a Chinese-language context. Under the policy rule, a forced language/locale without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.