Security audit
Security checks for vulnerabilities and agentic risk
This skill is a requirement-analysis template with disclosed file/URL reading needs and no evidence of hidden execution, exfiltration, persistence, or destructive behavior.
Install/use this for structured QA requirement analysis, but avoid feeding it real customer, payment, identity, or production data unless sanitized. Do not run the optional npx install command for the larger skill set unless you trust the source and are comfortable installing unpinned remote content.
The manifest content instructs the skill entirely in Chinese and presents Chinese trigger phrases and output conventions, but it does not state that the skill is region-specific or provide opt-in for another language. Under the policy, forcing a specific language without user choice is a natural-language policy concern.
The trigger guidance includes very broad phrases like “分析这个需求” and “需求分析,” which can match ordinary conversation and cause the skill to activate when the user did not explicitly intend it. Unintended invocation can pull unrelated user content into a structured workflow, increasing data exposure and creating confusing or unsafe tool use in contexts involving sensitive requirement documents.
The when-to-use field describes activation on uploaded PRDs, requirement documents, or any situation where deeper analysis may help, which is overly broad and weakly bounded. This raises the chance of accidental skill selection on sensitive artifacts and increases unnecessary processing of documents that may contain internal business logic or personal data.
The skill instructs users to run npx skills add Kokxi/qa-test-skills without pinning a version or integrity identifier. That creates a supply-chain risk: a later compromised or malicious package release could be fetched and executed unexpectedly on the user's system.
