Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language investment-analysis skill made of Markdown guidance and templates, with no code, persistence, credentials, or system-level access.
Install only if you want Chinese-language Wu Jun-style investment analysis templates. Verify any financial conclusions independently and ask the agent to use your preferred language or avoid personalized buy/sell advice if needed.
The document title and description are written entirely in Chinese and frame the skill as centered on Chinese investment wisdom, but there is no indication that language is optional or that the skill is region- or locale-restricted. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
The trigger phrases are broad and loosely scoped, such as generic requests about technology trends or investment views. This can cause the skill to activate in unintended contexts, increasing the chance of unsolicited financial-analysis behavior or context hijacking when a user did not clearly request this specific skill.
The activation guidance is broad enough to trigger on generic AI trend, investment, and forecasting questions, which can cause the agent to inappropriately steer conversations into this skill even when the user did not request this framework. In security terms this is a scope-control weakness: overbroad routing can override user intent, increase hallucinated domain authority, and lead to ungrounded investment-style advice being applied too widely.
The skill is written entirely in Chinese and appears to assume Chinese-language interaction without any opt-in, fallback, or locale rationale. This can cause the agent to respond in an unexpected language, reducing transparency, degrading user comprehension, and increasing the chance that important caveats—especially around investment analysis—are misunderstood or missed.
The document title and core description are presented only in Chinese, with no indication that other languages are supported or that the language choice is optional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
The description says the skill applies when a user needs 'data-driven' investment analysis, asks 'how to analyze a company with data,' does quantitative analysis, or applies Wu Jun's ideas. These conditions are high-level and overlap with many common investing or company-analysis requests, without clear constraints or negative examples to distinguish when this skill should or should not activate.
The entire template is written in Chinese and presents all section headings, labels, and instructions only in Chinese, which effectively imposes a specific language on users. The file does not indicate that Chinese is optional, user-selected, or required for a region-specific compliance purpose.
The skill is entirely written in Chinese and implicitly assumes a Chinese-language interaction without any opt-in or fallback behavior. This can create misfires, user confusion, or unsafe misunderstandings if invoked in a different locale, especially in a financial-advice context where nuanced interpretation matters.
The document title and description are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a China-specific audience. Under the policy rule, a skill that implicitly forces a specific language without opt-in can be a natural-language policy violation.
The entire template, including the title, section headers, and guidance text, is written only in Chinese with no indication that users may choose another language or locale. This can violate language/locale policy when a skill is expected to support user choice rather than enforce a single language by default.
No suspicious patterns detected.
