Security audit
Security checks for vulnerabilities and agentic risk
This is a read-only QA scenario-tree helper with disclosed sensitive-data cautions; the main caution is an optional unpinned install command for a broader skill set.
Use this skill for Chinese-language QA scenario-tree work, and avoid pasting real customer, identity, payment, or production data. Before running the optional `npx` install command for the broader skill set, review the source and prefer a pinned version or trusted release.
The activation guidance includes broad phrases like '构建场景', '测试场景', and '场景设计', which are common in normal QA discussion and can cause unintended invocation. If auto-invoked, the skill could process sensitive requirement or test data in contexts where the user did not intend to use this workflow, increasing the chance of over-collection, confusion, or unsafe downstream actions.
The when-to-use field defines activation conditions using broad natural-language examples rather than strict criteria, making accidental triggering plausible. In agent ecosystems, ambiguous activation can cause the wrong skill to run, leading to unintended access to workspace data or generation of outputs that the user did not request.
The skill instructs users to run npx skills add Kokxi/qa-test-skills without pinning a specific package version or immutable source reference. This creates a supply-chain risk: a future compromised or maliciously updated package could be fetched and executed at install time, and npx commonly executes remote package code during resolution/install.
This markdown template forces a specific language/locale for all users through its headings, instructions, and examples. Under the policy, language-specific constraints should either offer user opt-in/choice or be clearly justified as region-specific; neither is present here.
The entire skill reference is written in Chinese and does not indicate that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
