Back to skill

Security audit

股票操盘宝典

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese A-share trading-methodology skill with no code execution or data access, but users should treat its trading outputs as educational rather than personalized financial advice.

Install only if you want Chinese-language educational help applying 《股票操盘宝典》 style A-share trading frameworks. Do not treat its buy/sell/position outputs as personalized investment advice or as a guarantee; verify current market data, consider your own risk tolerance, and consult a licensed professional for real trading decisions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (22)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file gives detailed trading methodology, position sizing, timing, and buy/sell rules that a user could reasonably treat as actionable financial guidance, but it does not present a prominent upfront warning that the content is educational only and can cause financial loss. Although the text contains some caveats about limitations and avoids explicit stock tips or leverage, the operational framing ('可执行规则', specific仓位上限, indicators, entry/exit logic) increases the chance of real-world reliance and harm.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list contains broad terms like 'A股', '牛市', '熊市', '择时', '买点', and '卖点' that are common in general finance conversations. This can cause the skill to activate in contexts where the user did not ask for this specific book-derived framework, increasing the chance of unsolicited financial guidance and context-inappropriate responses.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill provides detailed trading process guidance, buy/sell timing concepts, position sizing, and risk-control rules, but does not prominently state that outputs are educational, non-personalized, and not financial advice. In a finance context, that omission can cause users to over-rely on the system for real investment decisions, especially because the content is framed as an actionable 'complete trading process' and 'system signals'.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad, common trading questions such as '能不能买' or '该不该卖', which can cause the skill to activate in ordinary conversational contexts and produce highly actionable financial guidance. Because the skill is designed to emit explicit buy/sell/hold outputs, unintended activation increases the chance of users receiving prescriptive advice without sufficient context, suitability checks, or escalation controls.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The execution steps instruct the agent to produce concrete '买/卖/观望' conclusions based on market indicators, but the skill does not prominently require a financial-risk warning or constrain outputs to general education. In context, this is more dangerous because the subject matter directly affects user assets and the surrounding text frames the method as a repeatable executable trading system, which may cause users to over-trust the output as personalized financial advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases include generic indecision language such as '该进还是该等' and '该不该动手', which can match users outside the intended A-share trading context. In a routed agent system, this can cause the skill to activate for unrelated decisions and then produce trading-oriented guidance where it is not appropriate, increasing the chance of harmful or confusing outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The execution section directs the agent to convert a market judgment into executable actions like '持有/卖出/进场/等待/减仓' without any warning that the content is educational and not personalized financial advice. Because the skill operates in a financial domain affecting user assets, omission of risk and suitability disclaimers makes the outputs more likely to be relied on as concrete advice, which can lead to monetary harm.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file’s headings and instructional content are written in Chinese throughout, while also including only a single English trigger example. This creates a natural-language locale constraint without any explicit opt-in, language selection, or justification that the skill is intended only for Chinese-language use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are broad enough to activate on ordinary market discussion, which can cause the agent to deliver prescriptive investment guidance in contexts where the user did not explicitly ask for this specialized skill. In a financial domain, over-broad activation increases the chance of unrequested or misplaced advice, making the skill more influential and risky than intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill gives actionable guidance such as whether to enter, hold cash, or trade by regime, but does not clearly warn that this is not financial advice and may materially affect investment decisions. In the surrounding context, the method is presented as a repeatable decision framework, which can lead users to rely on it as authoritative trading direction despite acknowledged market-regime limitations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger set is broad enough to activate on ordinary investing or risk-management questions without strong exclusion logic, which can route users into this skill when they did not ask for this specific framework. In a financial-advice context, misrouting is more sensitive because the skill contains prescriptive position-sizing guidance that could be inappropriately applied outside its intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The entire skill is written and structured only in Chinese, while also including an English trigger phrase, which suggests it may activate for non-Chinese-speaking users without any explicit language-choice mechanism. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This skill provides actionable stock-selection guidance, including screening criteria, watchlist inclusion, and candidate rejection logic, but does not clearly warn users that the output may influence financial decisions and can result in capital loss. In a retail-investing context, omission of a risk disclaimer can make speculative guidance appear more authoritative or safe than it is, increasing the chance of harmful reliance.

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 trading-action guidance such as identifying buy/sell points, waiting for confirmation candles, and explicitly outputting 'do not act/wait' versus entry conditions, but it does not include a clear financial-risk disclaimer or warning against relying on the content as investment advice. In a stock-trading skill, this omission increases the chance that users treat the guidance as actionable advice and incur financial losses, especially because the text presents the method as systematic and repeatable.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill content gives trading guidance that can be operationalized into real market actions, including suggesting that a user may 'consider entering the market' based on a bottoming signal. Without an explicit warning that this is educational content rather than financial advice, users may treat it as actionable investment guidance and incur monetary loss. In this skill context, the risk is elevated because the capability is specifically designed to guide A-share trading decisions, not merely discuss finance abstractly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill reference is written exclusively in Chinese and presents itself as global downstream context for later extractors and skills, with no indication that users may choose another language. This creates a natural-language locale constraint that appears mandatory rather than optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
62% confidence
Finding

The file is predominantly written in Chinese and its invocation examples are mainly Chinese, with only one English example, but it does not explicitly say the user can choose response language. This can create an implicit locale/language default without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

Natural-language policy violations include forcing a specific language without user opt-in. This file presents the entire skill in Chinese and includes user-facing trigger language in Chinese, with only one English example, but nowhere indicates that the user may choose another language or that the skill is intentionally region/language-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file contains primary instructional content in Chinese, with only limited English wording in headings and one trigger example. Under the policy rule for language/locale, forcing or assuming a language without explicit user opt-in can be a natural-language policy issue unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The trigger section uses broad phrases such as questions about building or following a trading system, which can overlap with ordinary financial discussion and cause the skill to activate outside its intended niche. In a finance domain, over-broad routing is risky because it may deliver operational trading guidance when the user only wanted general education, increasing chances of inappropriate or non-compliant advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
68% confidence
Finding

The file is primarily written in Chinese but includes a hard-coded English language trigger example under '语言信号' without clarifying whether the skill supports multiple languages by user choice. This can be read as an implicit language handling policy without explicit opt-in or documentation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file presents all titles, intents, and keywords exclusively in Chinese, with no indication that users may choose another language or that the locale restriction is intentional. Under the natural-language policy rule, forcing a specific language without user opt-in can be a policy violation.

Content

No source excerpt is available for this finding.