Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple AI-news headline fetcher; its web access is disclosed and purpose-aligned, with minor usability caveats but no evidence of malicious behavior.
Install this if you want a Chinese-formatted top-10 AI-news list from ai-bot.cn. Be aware it relies on one public website and may activate for broad AI-news requests, so users wanting multilingual output or multiple sources may need to specify that separately.
The skill hard-codes Chinese output and formatting without checking the user's language preference, which can override user intent and produce misleading or unusable responses in multilingual contexts. In agent systems, this is a policy and safety issue because it reduces user control and can silently cause incorrect task fulfillment.
The invocation condition is broad enough to trigger on common requests about AI news or trends, which can cause the skill to activate when the user did not explicitly ask to browse this specific source. That increases the chance of unnecessary web access, unintended delegation, and source bias by routing generic queries into a single-site scraping workflow.
No suspicious patterns detected.
