Security audit

段永平投资判断 · 价值投资方法论

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese markdown-only investing framework skill with clear financial disclaimers and no code, network access, persistence, or hidden authority.

Install only if you want a Chinese-language educational value-investing framework. Do not rely on its output as the sole basis for real-money decisions; verify current financial data and consider qualified professional advice.

A.I.G

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

SkillSpector

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 (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 79% confidence
Finding: Although the README says the skill is not investment advice, it prominently describes helping users decide whether an investment is worth making and applying a decision framework to specific stocks. For a markdown skill description, this can affect user finances, and the warning does not explicitly advise users to verify independently or avoid relying on the output for real-money decisions beyond a brief disclaimer.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger examples are broad enough to activate on generic investment-decision questions, which can cause the skill to engage in high-stakes financial contexts beyond a narrowly scoped educational framework. In a financial skill, overbroad triggering increases the chance that users receive quasi-advisory guidance when they may only be discussing investments generally, creating compliance, safety, and user-harm risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The activation conditions are broad enough to trigger on general investment, business, and decision-making conversations, which can cause the skill to engage outside a clearly bounded use case. In a financial domain, over-broad routing is risky because users may receive quasi-investment guidance in ambiguous contexts where the system has not established suitability, jurisdictional constraints, or whether the user is seeking regulated advice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown skill presents all instructions, triggers, and decision templates exclusively in Chinese, which effectively forces a specific language experience. The file does not offer multilingual support, user opt-in, or any explanation that the skill is intentionally limited to a Chinese-speaking audience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The entire skill description is written in Chinese and presents the skill as operating in that language, with no indication that users may choose another language or locale. Under the language/locale policy, a forced language without opt-in can be a natural-language policy concern unless clearly documented as region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.