Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese debugging workflow skill with disclosed local note-writing guidance and no hidden code, network retrieval, or installer behavior.
Install this if you want a strict Chinese-language root-cause debugging workflow. Before use, be aware that it may encourage rollback validation and creation of local memory/debug_log.md and memory/lessons.md files; keep control over any actual code reverts or documentation updates.
The trigger phrases are broad enough to match common debugging requests like '诊断' or '帮我分析原因', so the skill may activate in many ordinary conversations without clear user intent to invoke this specific workflow. That can cause unintended behavior override, such as forcing a rigid process, rollback guidance, or file-writing steps in contexts where they are inappropriate or unsafe.
The description, instructions, and example dialogue are entirely in Chinese and present the workflow as mandatory, but the file does not indicate that Chinese is optional or that the skill is region-specific. This creates a language/locale policy concern because it implicitly constrains interaction language without user opt-in.
The description embeds very broad trigger phrases such as '诊断', '帮我调试', and '排查问题', which are common in ordinary support conversations and can cause the skill to activate outside narrowly intended contexts. Over-broad activation increases the chance of unintended workflow hijacking, where the assistant is pushed into this skill’s rigid process even when the user did not explicitly request it.
The natural-language description is written to require operation in Chinese and does not offer any language or locale choice to the user. This can violate language or locale policy where skills must not force a specific language without explicit user opt-in or documented justification.
No suspicious patterns detected.
