Back to skill

Security audit

价值分析师

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese value-investing analysis skill with no executable behavior, but users should treat its buy/safety labels as educational screening rather than financial advice.

Install only if you want a Chinese-language Graham/value-investing screening aid. Verify all market data independently, treat its recommendation labels as informational, and do not make trades solely from the skill output.

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire README is written in Chinese, beginning with the title on L01, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. 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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description includes broad, conversational triggers such as asking whether a stock is 'safe' or requesting initial screening, which can cause the skill to activate on ordinary financial discussions without a clear, narrow scope. In a finance context, overbroad activation is risky because it can inject authoritative-seeming investment analysis and recommendations where the user did not explicitly request structured valuation guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill provides direct recommendation labels such as '强烈买入', '买入', '观察', and '不买入' without an explicit warning that the output is educational information rather than financial advice. Because the skill presents a systematic framework and concrete action language, users may rely on it as personalized investment advice, increasing the risk of financial harm or regulatory issues.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown skill/example forces a specific language for all user-facing content, which can violate language or locale policy when no user opt-in or alternative is provided. The document contains no indication that Chinese is optional, configurable, or required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language instructions, parameters, and outputs are entirely in Chinese, and the skill does not indicate that language selection is optional or user-configurable. Under the stated policy, forcing a specific language without user opt-in can be a language/locale policy violation unless clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

该文件全文以中文呈现,且未说明这是特定地区/语言受众限定的参考资料,也未提供用户可选择其他语言或本地化的说明。根据规则,强制特定语言且无用户选择或明确合理性说明,属于自然语言层面的语言/区域策略问题。

Content

No source excerpt is available for this finding.