Security audit
Security checks for vulnerabilities and agentic risk
This is a simple planning-template skill with no executable package code, persistence, credential access, or hidden data handling.
Install this if you want a Chinese-oriented implementation-plan template. Be aware that generic planning words may invoke it when you did not specifically intend to use this skill.
The manifest description is written entirely in Chinese and presents the skill behavior in that locale without indicating that users may choose another language. Under the policy, language constraints should be optional or clearly justified; no such opt-in or justification is present here.
The activation phrases are very broad ('计划 / 规划 / plan / 方案') and are likely to match ordinary user conversation, causing the skill to trigger when not explicitly intended. In an agent setting, this can lead to unintended workflow hijacking, where normal requests are routed through this planning skill and the assistant produces structured plans instead of following the user's actual intent.
No suspicious patterns detected.
