Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language scam-analysis reference skill with no executable code, hidden actions, persistence, or unusual privileges.
Install this if you want Chinese-language scam-pattern analysis. Be aware that it may trigger on broad credibility or trustworthiness questions and may respond in Chinese unless your agent adapts the output language.
The skill’s trigger scope is very broad: it covers nearly any question about whether an opportunity, product, service, investment, or cooperation is trustworthy. In an agentic environment, this can cause over-triggering on ordinary advice or credibility questions, leading the skill to dominate unrelated conversations and produce overly suspicious scam-oriented judgments.
The skill description is entirely Chinese and prescribes a Chinese-language workflow/output without offering language negotiation or a region-based justification. This can cause the agent to respond in an unexpected language, reducing usability and potentially causing misunderstanding in safety-sensitive scam assessments.
The document title and all instructional content are written entirely in Chinese, and the file does not indicate that Chinese is optional or that the skill is specifically restricted to a Chinese-speaking or region-specific context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
The entire document is written in Chinese and provides no indication that language selection is optional or that the content is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation.
No suspicious patterns detected.
