Security audit
Security checks for vulnerabilities and agentic risk
This is a general coding-assistant skill with disclosed coding workflows, command use, subtask spawning, and local task logging, with no artifact-backed evidence of deception or exfiltration.
Before installing, be aware that this skill is intended for Chinese-language coding workflows, can run commands and spawn subtasks as part of development work, and keeps local memory logs of coding-task outcomes. Avoid including secrets in task descriptions or code comments that could be captured in those logs.
The natural-language instructions and examples are entirely in Chinese, which effectively imposes a specific language on users. There is no indication that this is optional, user-selected, or required for a region-specific purpose.
The activation criteria are very broad and match common software-development requests such as writing code, fixing bugs, refactoring, and code review. This increases the chance the skill will auto-activate in situations where the user did not explicitly intend to invoke its behavior, including its logging and command-execution workflows, which can lead to unintended actions and expanded attack surface.
The skill states that every coding task is recorded to memory/YYYY-MM-DD.md, but it does not prominently warn users before activation that their prompts, file names, modifications, and rationale may be persistently stored. In a coding context, this can capture sensitive source code details, secrets, internal paths, or proprietary project information without informed consent.
The package description is written solely in Chinese, which creates an implicit language constraint without any indication of user opt-in or alternative locale support. Under the policy, language-specific behavior should either offer a choice or clearly document a justified regional restriction.
