Back to skill

Security audit

Grok Bot平替:常驻助理任务分派台

Security checks for vulnerabilities and agentic risk

Overview

The skill is a Chinese task-routing workflow with clear limits, user authorization requirements, and no hidden execution or persistence behavior in the inspected artifacts.

Before installing, make sure you are comfortable with a Chinese-language workflow that may connect to AI-HIVE for model/tool execution. Use it only with scoped materials, confirm pricing and budgets before paid work, and give separate explicit approval for any external send, payment, deletion, publication, upload, or business-system change.

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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description presents an always-on assistant product for task routing and assistant-like workflow continuity. The supplied code does something materially different: it validates saved result records offline for structural correctness, provenance fields, authorization references, and local artifact hashes. It has no triggers, no communication/channel integrations, no memory management, no assistant interaction logic, and no tool orchestration beyond reading local files. This is a clear description-behavior mismatch, with the actual code serving as a validator utility rather than the described assistant capability.

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
91% confidence
Finding

The display name, short description, and default prompt all require Chinese-language interaction, but the file does not indicate that this skill is intentionally limited to Chinese users or provide any user opt-in for language selection. This can violate language/locale policy because it forces a specific language by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file’s natural-language instructions and documentation are presented only in Chinese across the entire document. Under the language/locale policy rule, forcing a specific language without giving the user a choice or documenting a justified locale constraint is a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s instructional content is presented only in Chinese, which can amount to a language/locale policy violation when no user opt-in or alternative language path is provided. The document does not state that the skill is limited to Chinese-speaking users or a China-specific compliance context.

Content

No source excerpt is available for this finding.