Security audit
Security checks for vulnerabilities and agentic risk
This skill is a documentation-only academic writing report aggregator with some quality and trigger-scope caveats, but no hidden execution, credential access, persistence, or destructive behavior.
Installers should be aware that this skill is narrowly useful for aggregating English psychology Discussion-section diagnostics. Its broad Chinese triggers may activate unexpectedly, and one merge-rule reference should be clarified, but the reviewed artifacts do not show dangerous permissions or hidden behavior.
The Chinese trigger phrase set includes broad terms such as '全套诊断' and '完整讨论报告', which can plausibly match ordinary user requests beyond this narrowly intended skill. That creates an overbroad activation surface where the aggregator may be invoked unintentionally, causing misrouting, unexpected multi-skill execution, or application of a psychology-paper diagnostic workflow to unrelated content.
This markdown file presents the skill guidance primarily in Chinese, starting from the title and continuing through the operational instructions, without offering a language choice or explaining that the skill is intended only for a Chinese-speaking context. That creates a natural-language locale policy concern under the rule for forced language or locale without opt-in.
The file contains a self-contradictory policy section: it introduces cases that 'should not be merged' and then immediately says some of those cases actually should be merged. In an aggregation skill, contradictory merge rules can cause inconsistent or manipulated outputs, leading the agent to suppress, combine, or mis-rank issues unpredictably.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents headings, instructions, and analysis primarily in Chinese while embedding substantial English content, but nowhere indicates that the skill is Chinese-only or offers the user a language preference, which can amount to forcing a language without opt-in.
This markdown file presents nearly all instructional and evaluative content in Chinese, while retaining some English technical terms, and it does not state that the skill is intended only for Chinese-speaking users or offer an opt-in language choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
This file contains substantial natural-language instructions and headings in Chinese, including evaluation guidance and action plans, but does not indicate that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale limitation is documented and justified.
The title and purpose section present the rubric as an official standard in Chinese, and the rest of the document continues in Chinese/mixed Chinese-English without any indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
The description states the skill is for an "English psychology research paper," while the manifest also includes Chinese trigger phrases. This creates a natural-language policy concern because the file implies cross-locale invocation behavior without stating whether users can choose output language or that English-only processing is an intentional, documented constraint.
This markdown file contains natural-language guidance that presents the template as an official output format while using Chinese headings and instructions alongside English report sections. Because the file does not state that the skill is region-specific or provide an opt-in language choice, it can be read as imposing a specific locale/language convention on users.
