Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only skill for generating Chinese LLM trend reports, with web search instructions that fit its stated purpose and no evidence of hidden execution, persistence, credential access, or data exfiltration.
Install this if you want Chinese-language LLM trend reports that use current web research. Be aware that it may activate for broad AI-frontier or model-dynamics requests, and one referenced file, references/papers-trends.md, is mentioned but not included in the package.
The activation text uses very broad trigger phrases such as LLM trends, AI frontier, technical prediction, and model dynamics, which can overlap with many ordinary AI-related user requests. This can cause the skill to activate when the user did not specifically ask for a trend report, leading to unintended tool routing, irrelevant behavior, or overshadowing more appropriate skills.
The skill content is written to produce Chinese-language output by default and does not provide a user language choice. While not directly enabling code execution or data exfiltration, this can violate user expectations, reduce usability, and create routing or response mismatches in multilingual environments.
No suspicious patterns detected.
