Back to skill

Security audit

一句话交办助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed task-delegation drafting and validation skill with optional AI-HIVE/MCP use, not a hidden background executor.

Install only if you are comfortable using a Chinese-language workflow and, when AI-HIVE/MCP is used, reviewing the discovered tools, upload scope, pricing, and budget before any paid or external action. Keep the default draft-first mode unless you explicitly authorize sending, paying, deleting, 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill description promises a task-delegation assistant with optional AI-HIVE/MCP-backed execution, but the documented behavior appears centered on offline validation and references to external connection flows without clearly implementing the stated transformation/output behavior. This mismatch can mislead users or orchestration systems into invoking the skill in inappropriate contexts, causing unsafe overtrust, skipped review, or incorrect assumptions about what external actions were or were not actually performed.

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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger language is broad enough to match many normal assistant requests involving personal assistance, secretary-like help, or task delegation. Overbroad activation boundaries can cause the skill to intercept unrelated requests, steer workflows unexpectedly, or introduce unnecessary external-service guidance into benign conversations, increasing the chance of privilege confusion and unsafe task routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The phrase '适用于个人AI助理等需求' is ambiguous and does not clearly distinguish when this skill should be used instead of normal assistant behavior. In multi-skill or agentic environments, this ambiguity can cause accidental invocation, unnecessary collection/structuring of user task details, and confusion about whether the system is merely drafting artifacts or actually initiating real-world actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all user-facing policy and scope information exclusively in Chinese. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire workflow is written as a Chinese-only operating instruction set, with no indication that users may choose another language or that the skill is limited to a Chinese-specific compliance or regional context. Under the stated policy, imposing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.