Back to skill

Security audit

Manus Cue平替:跨渠道办事交接助手

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Chinese-language task handoff workflow with cautious AI-HIVE integration guidance and an offline result checker; I found no hidden persistence, credential theft, exfiltration, or automatic high-impact action.

Install only if you are comfortable using a Chinese-language workflow and, when needed, connecting to AI-HIVE through its official web or OAuth/MCP flow. Do not paste passwords, tokens, cookies, verification codes, or full identity documents into task records; confirm upload scope, prices, and any send/pay/delete/publish action separately.

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 (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description presents an operational cross-channel assistant that helps users hand off and execute tasks across devices/channels with authorized tools. The supplied code does something much narrower and different: it validates saved result records and local artifact metadata/hashes offline. It neither performs assistant-style task intake nor coordinates execution across channels, devices, or tools. While the code is safe and constrained, its primary purpose is materially different from the declared product description, so this is a clear description-behavior mismatch.

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.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The entire skill document is written as a fixed Chinese-language output contract and does not indicate that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire workflow is written as a Chinese-only operational specification and does not indicate that users may choose another language or locale. Under the stated policy, a skill that effectively enforces one language without opt-in or a documented regional justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language note is written only in Chinese and provides mandatory usage guidance, which can impose a language constraint on users without opt-in. The file does not indicate that this skill is intentionally limited to Chinese-speaking users or a China-specific context.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The docstring says this file performs offline validation of structure, local file hashes, and explicit record invariants, and does not assess truth or tool capability. However, the validator also enforces workflow semantics such as requiring authorization references for mutating actions, forbidding completed-but-unexecuted records, and requiring provider receipts for external mutations, which goes beyond purely structural and hash validation into business-rule validation of execution claims.

Content

No source excerpt is available for this finding.