Back to skill

Security audit

Kimi Work、QoderWork与扣子:项目资料续办助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language workflow skill for AI-HIVE-assisted project handoff and result checking, with no hidden persistence, credential capture, or automatic high-impact actions found.

Install this only if you want a Chinese-language AI-HIVE workflow for project handoff and deliverable validation. Before using AI-HIVE or any external service, confirm the upload scope, budget, and exact action; do not paste passwords, tokens, verification codes, cookies, or full identity documents into the workflow.

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 declared purpose frames the skill as a platform-comparison and task-handoff assistant, but the content also implies local filesystem inspection, structural validation, hashing, and secret-pattern scanning of saved JSON. That mismatch is dangerous because users may consent to a planning workflow without realizing the skill can inspect local artifacts and execution records, which can expose sensitive files or metadata beyond the expected task scope.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding

The skill references local files and an offline validation script but does not declare any explicit tool scope or allowed-tools boundaries. That creates an authorization ambiguity where an agent runtime may permit filesystem reads more broadly than the user expects, increasing the chance of unintended local data exposure during artifact checking.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger conditions are broad and overlap with many common requests about product comparison, unfinished work, deliverables, and agent integration. Overbroad routing can invoke this skill in contexts where the user only asked for general advice, causing unnecessary access to project materials or execution of higher-privilege workflow steps not actually needed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The note is written only in Chinese and provides mandatory user guidance, which can impose a language constraint on users without opt-in. The file does not indicate that this skill is region-specific or offer an alternative language choice, 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

This markdown file presents all operational guidance in Chinese and does not indicate that language selection is optional or user-configurable. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

All user-facing instructions and operational guidance in the skill are presented in Chinese, and the file does not state that the skill is Chinese-only or offer an alternative language path. This can violate language/locale policy when users have not explicitly opted into that language.

Content

No source excerpt is available for this finding.