Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward regression-test helper that recommends test cases from built-in templates and does not show hidden data access, persistence, or destructive behavior.
Install this if you want a Chinese-language regression test planning helper. Be aware that its activation keywords are broad, so it may appear during general regression-testing discussions, and its recommendations come from a fixed built-in template library rather than your actual test-management system.
The trigger phrases are short and generic enough to overlap with normal testing discussions, which can cause the skill to activate unintentionally in unrelated conversations. In an agent setting, accidental invocation can lead to context leakage into the skill, unexpected workflow changes, or incorrect recommendations being treated as authoritative test guidance.
The trigger phrases include very generic terms such as “回归测试”, “测试建议”, and “regression test”, which are likely to appear in ordinary developer or QA discussions. This can cause the skill to activate unintentionally and influence conversations or workflows without an explicit request, especially in environments where multiple skills compete for similar testing-related prompts.
The activation keyword at line 31 is broad enough that ordinary testing-related conversation may unintentionally trigger the skill outside a clear regression-testing request. In agent ecosystems, overbroad activation can cause unintended invocation, context capture, or misleading recommendations when the user did not actually intend to use this skill.
The keyword at line 34 ("regression test") is generic and can appear in many normal engineering discussions, making reliable intent matching difficult. This raises the risk of accidental activation and unwanted skill behavior, especially in shared or automated environments where agent actions should be tightly scoped.
This markdown file contains user-facing guidance exclusively in Chinese, starting from the title and continuing throughout the document. Under the policy rule for natural-language violations, forcing a specific language without user opt-in or an explicit justified regional scope is a locale-policy concern.
This README presents the skill exclusively in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. That can be a natural-language policy concern when a skill effectively forces a specific language without opt-in.
The display name, description, keywords, and categories are entirely in Chinese, while the manifest does not indicate that the skill is region-specific or that users can opt into this locale. This can constitute a language/locale policy concern when a skill presents itself in a fixed language without documenting choice or justification.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructional content only in Chinese, with no indication that the skill is region-specific or that users can opt into this language.
This code file contains natural-language descriptions, user-facing error messages, and formatted output entirely in Chinese. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the constraint is explicitly documented and justified.
No suspicious patterns detected.
