Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only QA test strategy skill with no executable payload, persistence, or data exfiltration behavior found.
Before installing the broader workflow mentioned by the skill, review the source and prefer a pinned, trusted package version. Expect Chinese-language QA strategy templates and verify that the skill only activates when you actually want a test strategy document, not for unrelated QA implementation questions.
The natural-language description and trigger guidance are written as mandatory Chinese usage conditions, while the file does not state that the skill is region-specific or offer alternative language behavior. This may violate language/locale policy because it effectively constrains interaction to a specific language without explicit user opt-in.
The activation list includes broad phrases such as "怎么测", "方案设计", and "测试范围", which can appear in ordinary conversations without the user intending to invoke this specific skill. The description does not provide negative examples or clear boundaries distinguishing when this skill should be used versus related QA planning skills.
The manifest says to use the skill when the user mentions phrases like "测试计划" or "需要制定测试策略", but it does not clarify whether casual mention, comparison, or downstream implementation questions should activate it. Without constraints or disambiguation, this can cause unintended invocation among adjacent QA skills.
The skill recommends running npx skills add Kokxi/qa-test-skills without any version pinning or integrity control. That creates a supply-chain risk: users may fetch and execute whatever package version is current at invocation time, including a compromised or typosquatted release.
This markdown file contains natural-language instructions exclusively in Chinese, which can constitute a language/locale policy violation when no user opt-in or audience restriction is stated. The file does not indicate that it is intended only for a Chinese-speaking or region-specific context, nor does it offer an alternative language option.
Line L025 states that the skill '仅在 workspace/ 输出评估文件' and does not persist or exfiltrate data. However, the manifest only allows Read/Grep/Glob at L007, which are read-only capabilities, and the rest of the file is documentation/template content rather than code that writes files. This is an active mismatch between the skill's own operational claim and what the skill definition supports.
