Back to skill

Security audit

Industry Research Analyst 行业研究分析师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language industry research assistant with an optional public market-data helper, and I found no hidden persistence, credential access, or destructive behavior.

Install only if you want a Chinese-oriented industry research workflow that may use web searches and public market data. Treat its investment ratings, stock comparisons, and suggested positions as research assistance, not financial advice, and verify cited sources before acting on them.

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 (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

声明描述的是一个高层次、结构化的行业研究技能,核心输出应是完整行业研究报告。实际代码并未实现这些分析能力,而是一个狭义的数据辅助工具,主要访问Yahoo Finance抓取个股市场数据,并将其格式化为Markdown表格。对于行业参数,脚本反而明确提示“仅获取股票行情数据”,并建议用户自行搜索市场规模和行业报告。这说明其真实主功能与声明存在显著偏差:从“深度行业研究生成”降级为“股票数据采集/比较辅助”。虽然公司对比可被视为行业研究的一个支持环节,但代码缺失声明中的大部分关键分析能力,因此构成明显不匹配。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding

The skill explicitly instructs the agent to perform web/data searches and use recent news, but it declares no tool scope or allowed-tools policy. That mismatch can lead to unintended network access or broader-than-expected tool use, reducing sandboxing and reviewability.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are very broad and overlap with ordinary research-related language, making accidental or silent activation more likely. If auto-invoked, the skill could initiate unnecessary searching, produce investment-oriented outputs, or steer conversations into a specialized mode the user did not explicitly request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language instructions are written entirely in Chinese and repeatedly frame analysis around Chinese market data and output patterns, but do not state that this is optional or user-selectable. Under the policy, a skill should not implicitly force a specific language or locale unless it clearly offers opt-in or documents a justified regional restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents the skill's output examples exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or alternative language option is provided. The instructions specify flagging cases where a skill forces a specific language without user choice, and no such choice or justification appears in the file.

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 title and introductory instructions are entirely in Chinese, and the document presents itself as a general execution framework rather than a clearly region-locked or language-specific tool. Under the policy, imposing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file's docstring, argument descriptions, and runtime guidance are written entirely in Chinese, which imposes a specific language on users. The skill does not offer an English alternative, language selection, or explain that it is intentionally limited to a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.