Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent Chinese AI-news briefing workflow that fetches public news, translates it, and can push the result to configured messaging channels.
Install this if you want a Chinese-language AI news digest. Before enabling scheduled delivery or the message tool, set the exact Feishu, Telegram, or Discord destination and use a manual run first to confirm the content and channel.
The skill advertises automatic pushing to Feishu, Telegram, and Discord but does not present a clear user-facing warning that content may be sent to external messaging platforms. This weakens informed consent and increases the risk of unintended data transfer, spam, or disclosure of translated/generated content to third-party services or group channels.
The manual trigger phrase is generic enough to match an ordinary user request for news collection, which can cause the skill to activate unexpectedly without clear user awareness that its specific workflow will run. Because the workflow includes external fetching and possible downstream push behavior, accidental invocation could lead to unintended network activity or content delivery beyond what the user explicitly intended.
The formatting rules explicitly require headlines to be in Chinese, and the template fields and examples are also Chinese-centric. This creates a language-policy constraint without offering the user a language choice or documenting that the skill is intentionally region-specific.
This markdown file contains a natural-language instruction that all English-language source content is automatically translated to Chinese. That imposes a specific output language/locale choice without indicating any user opt-in or configurable language preference, which matches the language/locale policy violation criteria.
No suspicious patterns detected.
