Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Chinese-language reference skill with no code, credential use, persistence, or hidden behavior found.
Installing this skill should be low risk. Users should expect Chinese-language reference guidance about the named auto_llm_1644 topic; the main practical caveat is that its trigger wording may activate for broad related requests.
The trigger conditions are broad and loosely scoped: they activate not only on the exact skill name but also on a generic term and any request for related help. In an agent environment, this can cause unintended invocation, context hijacking, or routing of unrelated user requests into this skill, increasing the chance of misexecution or policy bypass through overmatching.
The skill description and instructional content are entirely presented in Chinese, with no indication that users can choose another language or that the skill is intentionally restricted to Chinese-speaking users. This creates a natural-language policy concern if the skill is expected to operate generally rather than as a clearly documented locale-specific tool.
No suspicious patterns detected.
