Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language advice framework with broad auto-activation cues, but it contains only markdown guidance and no hidden code, data access, persistence, or destructive behavior.
Install this if you want a Chinese, culturally styled coaching and decision-analysis prompt. Be aware it is designed to auto-apply on broad life, work, relationship, stress, and money-related cues, so users who want neutral responses or explicit opt-in only may prefer to narrow its trigger conditions before use.
The skill’s trigger definition is extremely broad, covering common emotional states and ordinary life topics such as anxiety, relationships, work pressure, and decision-making. This can cause the agent to invoke the skill in routine conversations without clear user intent, leading to prompt hijacking of the response style/behavior and reducing user control over when specialized guidance is applied.
The default auto-matching table maps vague phrases like '纠结', '累', '想骂人', or '学不进去' to framework activation, which are commonplace expressions in normal chat. Because the boundaries are undefined, the skill may over-trigger and steer responses into a prescriptive persona and decision framework even when the user did not request it, creating unintended behavioral override and potentially inappropriate advice in sensitive contexts.
Allowing combination mode for any 'multi-dimensional problem' is underspecified and effectively expands the skill’s scope to a very large share of user queries. This increases the chance of unexpected invocation, compounded behavior changes, and over-application of the skill’s framing to complex personal or professional matters where the user may only want neutral assistance.
This markdown file presents all framework instructions, examples, and output formats exclusively in Chinese, which imposes a specific language on users. The policy allows language constraints only when the skill offers opt-in language choice or clearly documents a justified region-specific limitation, neither of which appears here.
This markdown skill file presents all headings, instructions, examples, and output formats exclusively in Chinese, which can amount to a language-policy violation when no user language preference or opt-in is provided. The file does not state that it is region-specific or that users may choose another language.
This markdown file presents all framework names, instructions, and examples exclusively in Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the locale constraint is explicitly justified, which is not present here.
This markdown file contains user-facing guidance exclusively in Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy rule for language/locale constraints, forcing a specific language without user choice is a natural-language policy concern.
The entire skill is authored as Chinese-only instructional content and all output templates are specified in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language locale violation unless the regional constraint is explicitly documented and justified.
This file presents all instructions and framework content exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or justification is provided. The policy specifically calls out skills that force a specific language without offering a choice.
