Back to skill

Security audit

Duckbill替代流程:人工代办材料与进度管家

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language task-handoff workflow that keeps real-world actions gated on user authorization and evidence.

Install only if you are comfortable using a Chinese-language workflow and, when needed, authorizing AI-HIVE or other tools for specific tasks. Do not provide passwords, tokens, verification codes, cookies, or broad private datasets; confirm upload scope, budget, and any real-world action before allowing calls, payments, refunds, account changes, messages, 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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (11)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description presents an end-user assistant workflow for handling several real-world support/operations tasks via AI and authorized tools. The supplied code does none of that. It only validates a saved result file against a contract and local artifact hashes, explicitly stating it does not authenticate, call APIs, or execute actions. This is a materially different primary purpose, not just an internal helper detail for the described skill. No relevant assistant behaviors, user-facing task handling, reminders, follow-up flows, or external tool interactions are implemented in this code chunk.

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
91% confidence
Finding

The description says the skill is used when users compare Duckbill alternatives and want help with several assistant workflows, but it does not define a clear trigger boundary or explicit invocation phrases. This broad natural-language condition could match many general product-comparison or task-assistance conversations and cause unintended activation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill states it must not claim to have placed calls, yet the usage table labels the subflow as 'AI代打电话', creating a contradictory instruction set. In a human-handoff and external-action context, this can cause operators or downstream agents to misrepresent completed real-world actions, resulting in unauthorized commitments, false status reporting, or user reliance on actions that never occurred.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The '何时使用' column uses short phrases such as '退货助手' and '订阅管理' that are too generic to distinguish activation from ordinary discussion or adjacent tasks. Without constraints or negative examples, these conditions do not clearly define when each sub-workflow should or should not run.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description limits the skill to Duckbill-alternative workflows around appointment-call preparation/follow-up, returns/refunds, and subscription billing/renewal reminders. Line L27 expands the skill to a separate '房屋维修售后进度助手' capability, which is not mentioned in the manifest's stated purpose and changes the functional scope beyond the described Duckbill replacement scenarios.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata and default prompt are entirely in Chinese and do not indicate any supported language options or locale limitations. This can cause users or downstream agents to misunderstand instructions, consent, scope, or task outcomes, which is especially problematic in a handoff workflow involving materials, permissions, fees, and progress tracking.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

All user-facing example inputs and expected behaviors in this file are written exclusively in Chinese, with no indication that other languages are supported or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, language constraints should be optional or explicitly justified rather than implicitly enforced.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This file presents all user-facing guidance exclusively in Chinese, with no indication that the skill is region-specific or that users can opt into another language, which can amount to forcing a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file’s operational instructions, examples, and outputs are all presented in Chinese, which can force a specific language experience if the skill is used in a broader multilingual environment. The policy allows locale constraints only when user opt-in is offered or the restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This file presents all operational instructions and user-facing workflow content only in Chinese, with no indication that users can opt into 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 is a natural-language policy issue.

Content

No source excerpt is available for this finding.