Back to skill

Security audit

选股专家

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple Chinese stock-analysis guide, but it gives direct buy/sell-style investment recommendations without enough financial-advice guardrails.

Review this skill carefully before installing if you might rely on it for real investment decisions. Treat its outputs as an educational framework only, not personalized financial advice, and consider adding clear disclaimers plus prompts for time horizon, risk tolerance, and independent verification before any recommendation is shown.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The title and all visible documentation in this file are written exclusively in Chinese, with no indication that the user can choose another language or locale. Under the policy rule, a skill that forces a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata says it should activate whenever a user 'needs stock picking' or asks whether a company is worth investing in, which are broad, common triggers likely to over-invoke the skill in ordinary finance conversations. Overly broad activation can cause the agent to deliver prescriptive investment analysis in contexts where the user did not explicitly request this methodology, increasing the chance of unsuitable or overconfident financial guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill provides direct recommendation labels such as '强烈买入 / 买入 / 不买入' and investment scoring without a clear, proximate disclaimer that the output is educational and not financial advice. In this context, the structured recommendation language can be interpreted as personalized financial advice, which raises user-harm and compliance risk if relied on for real investment decisions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file gives concrete stock evaluation and a directional recommendation ('不买入', '观察') without a clear disclaimer that the content is informational only and not personalized investment advice. In a stock-picking skill, users may reasonably rely on this as financial advice, increasing legal/compliance risk and the chance of harmful financial decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire template, including headings and field labels, is written only in Chinese and provides no indication that users may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
62% confidence
Finding

全文仅以中文呈现,且未说明这是面向特定中文用户群体的区域性示例,也未提供语言选择或用户 opt-in。根据 SQP-3,若技能在自然语言层面隐含强制特定语言/locale 而没有选择机制,可能构成语言或区域政策问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.