Back to skill

Security audit

豆包手机助手、AutoGLM、Siri与Alexa:跨设备办事接力

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese workflow guide for cross-device task handoffs with explicit limits around credentials, authorization, uploads, payments, deletion, and external tool use.

Install this only if you want a Chinese-language workflow for coordinating task handoffs and AI-HIVE-assisted processing. Before using external AI-HIVE tools, confirm the official domain, tool list, upload scope, price, budget, and any action-specific authorization; do not paste passwords, tokens, verification codes, cookies, or full identity documents into task files.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description promises an end-user assistant that coordinates tasks across devices and channels, comparable to mobile/voice assistants and agent products. The supplied code does none of that. Its sole function is offline validation of a saved results record against a contract, including provenance/integrity checks on local artifacts. There are no integrations with phones, computers, screenshots, voice input, inboxes, external services, or cross-device workflows. This is a materially different primary purpose, not merely an implementation detail, so the description does not accurately represent the code.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises operational workflows that depend on reading local/reference files and potentially orchestrating external tooling, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates ambiguity about what the agent may access at runtime, weakening least-privilege controls and increasing the risk of unintended file access or overbroad execution in hosts that infer capabilities implicitly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language examples and expected behaviors are entirely specified in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language or region-specific context. Under the policy, forcing a specific language without opt-in or documented justification is a locale-policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This file contains user-facing natural-language instructions exclusively in Chinese, which can amount to a locale/language constraint. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file's instructions and workflow are entirely presented in Chinese, and there is no indication that the user opted into Chinese or that the skill is restricted to a Chinese-speaking context. This can violate a language/locale policy when a skill forces 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
86% confidence
Finding

The document’s operational instructions and user-facing workflow description are entirely in Chinese, which can force a specific language on users or operators without opt-in. The file does not state that the skill is region-specific or provide an alternative language option, so it may violate language/locale policy requirements.

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, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. This can violate language/locale policy because it forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The note field contains user-facing instruction text only in Chinese: it tells users not to fill in passwords, tokens, verification codes, cookies, or full identity-document information. For a general intake manifest, this imposes a specific language/locale without any opt-in or stated justification, which matches the language/locale policy-violation category.

Content

No source excerpt is available for this finding.