Security audit
Security checks for vulnerabilities and agentic risk
This skill is a markdown-only workflow for labeling evidence freshness; its query suggestions need care but do not show malicious or high-impact behavior.
Before installing, confirm that any compensation_queries produced by the skill are treated as recommendations unless your orchestrator intentionally allows automatic follow-up search. Chinese-only documentation may also be unsuitable for users who need English or multilingual instructions.
The documentation explicitly says the skill does not do search or supplement information, but later instructs it to auto-generate compensation search queries. This contradiction is dangerous because agentic systems often rely on natural-language contracts; conflicting instructions can cause policy bypass, unexpected retrieval, or prompt-routing errors in downstream automation.
The activation text says the skill should be used for broad categories like real-world questions, news, policy, and market analysis whenever a task is time-sensitive or needs to reduce stale-evidence risk. This describes a very wide class of ordinary research tasks without a precise invocation phrase, boundary conditions, or negative examples, which could cause unintended activation.
The natural-language description and title present the skill entirely in Chinese, with no indication that language is optional or that the skill is intended only for a Chinese-speaking or region-specific environment. Under the policy, a language constraint should either be user-selectable or clearly justified as locale-specific.
The skill claims to judge evidence freshness, but it also emits compensation search queries that can influence downstream retrieval behavior. This creates a scope-expansion/instruction-boundary issue: an orchestrator or later agent may treat these generated queries as authoritative tasking, causing unreviewed search pivoting beyond the skill’s declared function.
This markdown file is written entirely in Chinese, including headings, scenario descriptions, processing notes, and output commentary, with no indication that the user can choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
This markdown file presents the skill content entirely in Chinese, starting from the title, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language or region-specific context. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.
该 markdown 文件全文以中文编写，未见任何说明表示这是面向特定中文用户群体的区域性文档，也未提供多语言或用户选择语言的选项。根据语言/区域政策要求，若技能内容默认强制单一语言且无用户选择或合理限定，可能构成自然语言层面的政策违例。
No suspicious patterns detected.
