Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent QFD quality-management helper that uses local JSON/CSV files and scripts for matrix calculations without hidden network, credential, persistence, or privilege behavior.
Install this when you want Chinese-language QFD/House-of-Quality support and are comfortable running local Python scripts on project-local JSON/CSV files. Keep input and output paths in a dedicated workspace and review generated matrices before using them for business decisions.
The skill references local scripts and file-based inputs/outputs, implying read/write capabilities, but it does not declare any tool scope or permissions boundary. That can lead to overbroad agent behavior where the runtime may access files beyond what is necessary, increasing the risk of unintended data exposure or modification.
The trigger condition is phrased broadly enough to match generic product planning, prioritization, or specification tasks, which may cause the skill to activate in contexts beyond strict QFD analysis. Over-broad activation can route unrelated user requests into file/script-driven workflows, increasing the chance of unnecessary file access or misuse of the skill’s capabilities.
This code file includes natural-language descriptions and user-facing text exclusively in Chinese, and later CLI help/output strings follow the same pattern. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
No suspicious patterns detected.
