Security audit
Security checks for vulnerabilities and agentic risk
This skill is a markdown-only academic writing checker with no code execution, persistence, credential use, or hidden data handling.
Installers should expect a narrow academic-writing diagnostic aid. The main caveat is that its triggers are broad, so users may want to invoke it only when reviewing psychology research-paper Discussion sections and be aware that reference guidance is partly Chinese.
The manifest description says the skill triggers on phrases including "check conventions" and "contribution statement" plus "etc.", but it does not clearly bound when those phrases should or should not activate this specific academic-writing diagnosis skill. These phrases are broad enough to overlap with ordinary editing or discussion requests, increasing the chance of unintended invocation.
The trigger phrase at line 18 ("check conventions") is broad and likely to appear in many general editing or writing contexts, which can cause the skill to activate outside its intended domain. In an agent system, overbroad activation can route unrelated user content into a specialized skill, creating unintended data exposure, confusing behavior, or policy bypass if downstream handling assumes psychology-paper Discussion text.
The trigger phrase at line 19 ("contribution statement") lacks enough context to distinguish this academic Discussion-checking skill from many other writing, résumé, grant, or product-description contexts. This ambiguity increases the chance of accidental invocation and misrouting, especially in multi-skill environments where generic terms should not be used as sole selectors.
The trigger phrase at line 20 ("happy words") is highly ambiguous and colloquial, making it likely to collide with unrelated sentiment, wellness, marketing, or language-learning requests. Because the skill is intended only to diagnose hedging and evaluative language in psychology-paper Discussions, such an unconstrained trigger materially raises unintended activation risk.
This markdown file includes an activation/diagnostic description using broad internal criteria like "contribution type 判定" and "happy words 与 claim 匹配" without defining exact trigger phrases, boundaries, or negative examples. That ambiguity could cause the example to be invoked in cases beyond the intended narrow contribution-analysis context.
This markdown file presents all instructional and usage content in Chinese, including headings, analysis, and invocation guidance, with no indication that users may choose another language. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue.
This markdown file presents the skill guidance almost entirely in Chinese, including headings, analysis, and usage instructions, while also embedding some English academic phrases. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation, and this file does not state that the skill is intentionally limited to Chinese-speaking users or offer an alternative language option.
This markdown file presents the rubric title and purpose in Chinese and does not indicate that another language can be used or that the Chinese-only presentation is required for a specific regional or compliance reason. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
This markdown file is written primarily in Chinese with embedded English terms, but it does not state that the skill is region- or language-specific or offer the user an opt-in language choice. Under the natural-language policy rule, forcing a specific language or locale without user choice can be a policy concern.
No suspicious patterns detected.
