Security audit
Security checks for vulnerabilities and agentic risk
This skill is a low-risk writing-diagnosis guide for academic Discussion sections, with no executable code or privileged behavior.
Install this if you want structured feedback on vocabulary and hedging in psychology-paper Discussion sections. Be aware that broad triggers may activate it for more general vocabulary requests, and some reference guidance is written in Chinese or mixed Chinese-English.
The phrase "academic expressions" is vague and lacks sufficient domain or task boundaries, so it may activate on broad academic-writing queries unrelated to this specialized diagnosis skill. Ambiguous activation increases the chance of misrouting user intent and producing inapplicable analysis.
The phrase "academic expressions" is vague and lacks sufficient domain or task boundaries, so it may activate on broad academic-writing queries unrelated to this specialized diagnosis skill. Ambiguous activation increases the chance of misrouting user intent and producing inapplicable analysis.
The trigger phrase at line 18 ("check vocabulary") is broad enough to match many ordinary editing or language-help requests outside the narrow intended scope of Discussion-section psychology papers. This can cause unintended skill activation, leading to confusing routing, over-collection of user text, or application of the wrong analysis behavior even without malicious intent.
This markdown file contains natural-language instructions and guidance almost entirely in Chinese, but it does not state that the skill is region-specific or provide any opt-in for language preference. Under the policy rule, forcing a specific language without user choice is a natural-language policy violation.
The file title and core instructional sections are presented in Chinese or mixed Chinese/English, and there is no indication that users may choose another language. This can violate language/locale policy when a skill imposes a specific language without opt-in or documented regional justification.
The trigger phrase at line 19 ("academic expressions") is underspecified and likely to overlap with generic writing, ESL, and classroom requests. Because the skill is specialized, such a generic activation phrase increases the chance of accidental invocation and misapplication of the skill's diagnosis workflow.
No suspicious patterns detected.
