Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Chinese-language scheduled AI-news briefing skill that sends generated public-news summaries to WeCom, with no code execution, credential access, hidden payloads, or destructive behavior found.
Before installing, confirm that a daily 08:30 Asia/Shanghai WeCom announcement is desired, that the destination channel is correct, and that generated news summaries are acceptable to send automatically without human review.
The README is entirely in Chinese and the example scheduled payload instructs execution of a Chinese-language task, while the schedule is fixed to the Asia/Shanghai timezone. This indicates a specific language/locale is being imposed without an explicit opt-in or justification that the skill is intended only for a China-specific audience.
The README explicitly describes automatic delivery through external messaging channels but does not disclose that generated content will be transmitted out of the local agent environment. In a scheduled skill, this omission can cause users to unknowingly enable recurring outbound sharing of potentially sensitive summaries, prompts, or derived content to third-party platforms.
The skill describes automatic scheduled sending through external messaging channels but does not clearly warn users that it will send outbound messages on a timer. Lack of explicit disclosure and consent for autonomous external communication can cause unauthorized notifications, privacy issues, spam, or policy violations, especially if recipients or channels are preconfigured.
The skill description and output requirements are entirely Chinese-language and also hard-code a China-specific locale context with Asia/Shanghai timing and culturally specific content such as 黄历. There is no indication that users can choose language or locale, so the file appears to impose a specific language/locale by default without opt-in.
The manual trigger description ('directly call this Skill') is overly broad and does not define required authorization, scope, or whether triggering also sends outbound messages immediately. In a skill that gathers content and sends a daily briefing through messaging channels, ambiguous invocation semantics can lead to unintended execution or message dispatch by users or automations that were not meant to initiate sending.
The scheduled message instructs the agent entirely in Chinese and requires a Chinese-specific output format, while the file does not indicate that users opt into Chinese-language delivery or that the skill is restricted to a Chinese-speaking audience. This creates a natural-language locale policy concern because the skill appears to enforce a specific language by default.
The prompt is entirely written to generate the briefing in Chinese and does not provide any user opt-in or alternative language option. This is a natural-language locale policy issue because it imposes a specific language on all users without documented justification.
The skill is configured to automatically deliver generated content to WeCom in announce mode, but the configuration provides no user-facing disclosure, consent mechanism, or clear indication that outbound delivery happens on a schedule. This can cause unexpected data transmission and privacy or compliance issues if generated summaries include sensitive or organization-specific information.
The natural-language prompt requires output in Chinese and includes fixed Chinese-format sections and quotations, but there is no opt-in, language selection, or documented justification that this skill is limited to Chinese-speaking users or a China-specific deployment. This creates a language/locale policy concern because the skill effectively forces a specific language.
No suspicious patterns detected.
