Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only AI agent testing guide with no hidden execution, persistence, or data-exfiltration behavior found.
Install this if you want Chinese-language guidance for designing AI agent test cases and security checks. Be aware that its triggers are broad, so it may activate on general AI-agent testing discussions, and its declared Bash/WebFetch access should be used only for explicit validation or research tasks you approve.
Nearly all instructional content, field names, and output expectations are specified only in Chinese, while the file does not indicate that users may choose another language. This creates an implicit locale requirement without opt-in, which matches the language-policy violation criterion.
The trigger phrases are very broad and include generic terms like AI agent, LLM, chatbot testing, and AI security audit. This can cause the skill to activate in routine conversations that merely mention those topics, leading to unintended workflow steering, unnecessary tool exposure, or context hijacking away from the user's actual request.
The when-to-use field defines activation using ambiguous topic keywords without boundaries, disambiguation logic, or counterexamples. In an agentic system, ambiguous routing is risky because it may invoke this skill for unrelated requests and bias the assistant toward security-testing behavior the user did not ask for.
The document title and introductory instructions are entirely in Chinese, with no indication that language selection is optional or that the skill is intentionally limited to a Chinese-speaking context. This creates a natural-language policy concern because the file effectively imposes a specific language/locale on users without opt-in.
The skill content begins in Chinese and continues in that language throughout the document, which effectively forces a specific language for users of the skill. The file does not indicate that Chinese is optional, user-selected, or required for a documented region-specific purpose.
The entire skill reference is written in Chinese and does not indicate that other languages are supported or that Chinese is a region-specific requirement. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale policy violation.
This markdown file contains natural-language instructions and examples exclusively in Chinese, and it does not indicate that the skill is region-specific or that users may choose another language. Under the language/locale policy rule, forcing a specific language without opt-in is a policy concern.
No suspicious patterns detected.
