Security audit

Kline Master

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent trading-education skill with no hidden malware found, but it gives specific high-risk trading and leverage guidance with weak upfront safety framing.

Review this skill carefully before installing if you may rely on it for real trades. Treat its outputs as educational examples only, be especially cautious with leverage and exact entry/exit targets, and do not connect it to any trading account or act on recommendations without independent analysis or licensed financial 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
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (14)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared description presents a trading-analysis skill package for learning and applying K-line/candlestick trading techniques. The supplied code does not implement any market analysis, indicator calculations, pattern recognition, support/resistance logic, or trader-facing skill behavior. Instead, it creates a static cover image with stylized candlesticks, title/subtitle text, a price badge, and saves the PNG to disk. While the image content thematically references trading, the code’s actual purpose is asset generation for packaging/marketing, which is materially different from the declared skill functionality.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The activation rule '当用户询问交易相关问题时，自动调用此技能' is overly broad and can cause the skill to trigger on a wide range of ordinary finance or market conversations without clear user intent. Over-broad invocation increases the chance of unintended skill execution, inappropriate financial advice generation, and context leakage into conversations that did not explicitly request this specialized behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: This section provides high-risk leveraged contract trading guidance, including leverage suggestions, position sizing, and long/short mechanics, but the safety framing is insufficient and not prominently placed before the instructions. Because leveraged trading can rapidly cause liquidation or losses exceeding expectations, presenting actionable steps without a strong upfront warning materially increases user harm risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The document is primarily written in Chinese and presents publication and promotion instructions in that language without offering any language choice or stating that the skill is intended only for a Chinese-speaking audience. This can violate language/locale policy when a skill or its operational guidance imposes a specific language by default.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The sales copy promotes 'AI 实时指导' for trading decisions without any warning that trading is high-risk and that AI guidance can be inaccurate, delayed, or unsuitable for a user's financial situation. In the context of a retail-focused trading skill targeting inexperienced users, this can materially increase the chance that users over-trust the tool and incur financial losses.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill gives concrete entry, stop-loss, take-profit, and position-sizing recommendations that could directly influence users' financial decisions, but the risk disclaimer appears later and is not prominent before actionable advice is shown. In a trading context, this increases the chance users treat speculative output as reliable financial guidance and incur losses.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: All user-facing instructions, templates, and outputs in the file are specified in Chinese, and the document does not indicate that this language constraint is optional or region-specific. Under the language/locale policy, forcing a single language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file gives explicit trade instructions, position sizing, stop-loss/take-profit levels, and realized profit figures in a way that reads like actionable financial guidance rather than clearly labeled education. In a trading skill context, this can mislead users into treating historical examples as recommendations, increasing the risk of financial loss when users copy the setups without suitability checks or risk disclosures.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This section gives concrete buy/sell signals and trading actions such as '金叉买入，死叉卖出' without a clear, prominent warning that the material is educational only and not financial advice. Users may treat these simplified signals as actionable recommendations and incur financial losses, especially because the surrounding content is written as a practical trading guide rather than abstract theory.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file contains substantial Chinese-language framing alongside English product copy, but it does not state whether the skill supports multiple languages or is intended only for Chinese-speaking users. Under the language/locale policy, forcing or implicitly assuming a language without opt-in or justification can be a policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This checklist is primarily written in Chinese, but the section labeled '描述（英文版）' provides a fixed English description with no indication that the user can choose language or that English is required by the platform. That creates a natural-language locale constraint without explicit opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The skill documentation and sales messaging are exclusively in Chinese, which can amount to a language-policy issue when no opt-in or locale justification is provided. The file does not indicate that the skill is intentionally limited to Chinese-speaking users or provide alternatives.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The file presents the skill name, description, examples, and warnings only in Chinese. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file forces a single language/locale presentation through all headings and instructions, and there is no indication that the user can opt into another language or that the skill is intentionally region-specific. This matches the language/locale policy concern for natural-language content.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.