Back to skill

Security audit

Futures Radar

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public futures and commodity prices from Yahoo Finance and does not show hidden, destructive, or persistent behavior.

Install this only if you are comfortable with the skill making Yahoo Finance network requests for live market data. Expect Chinese-language output and broad activation around commodity or futures terms, but the inspected artifact does not request credentials, modify files, or install persistence.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill includes executable example code that performs outbound network access to Yahoo Finance, but the manifest does not declare any tool scope or permission boundary. This creates a transparency and governance gap: the agent may invoke network-capable behavior without an explicit contract, making review, sandboxing, and user consent harder.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad commodity- and market-related phrases such as '原油', '黄金', and '期货行情', which can cause the skill to activate in contexts where the user did not intend live data retrieval. Over-broad activation can lead to unnecessary network calls, context hijacking, or confusing responses from the wrong skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description and code show that it retrieves external data from Yahoo Finance, but there is no clear user-facing notice at invocation time that a third-party network request will occur. Lack of disclosure reduces informed consent and can surprise users in privacy- or policy-sensitive environments where external calls are restricted.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
77% confidence
Finding

文件整体说明与技能名称展示均固定为中文,且未说明可根据用户偏好切换语言或接受其他语言输入。若组织要求避免未经用户同意强制特定语言/地区设置,这种单一语言约束可能构成自然语言策略违规。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest frames the skill around commodities/futures queries such as crude oil, gold, silver, natural gas, copper, and broad commodity market monitoring. However, the implemented symbol set extends beyond commodities into rate products (10Y/30Y Treasury futures) and a macro FX index (DXY), which materially broadens the skill's functional scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The module description and user-facing output strings are all in Chinese, with no indication that the user can choose another language or that the locale is intentionally restricted. This can violate language/locale policy when a skill forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The script sends HTTP requests to an external Yahoo Finance endpoint, which exposes the user's system IP/addressing metadata and request details to a third party. While this network access is core to the skill's purpose, the code itself provides no explicit comment or warning that external requests are being made.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.