Security audit
Security checks for vulnerabilities and agentic risk
This news skill mostly aggregates public feeds, but it should be reviewed because it mixes removed monitoring and push features with active-looking persistence, cron, and optional long-running service instructions.
Install only if you are comfortable with broad public-source fetching and local news archives. Do not enable push channels, cron schedules, X/Twitter cookies, Playwright deep fetching, or Docker self-hosting unless you explicitly want those behaviors and can review the configuration.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
<!-- Omni News HTML邮件模板，参考自cclank开源项目 -->
<div style="max-width:600px;margin:0 auto;font-family:-apple-system,sans-serif">
<h1 style="color:#1a1a1a;border-bottom:3px solid #0066cc;padding-bottom:10px">
📰 Omni News 日报
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
<!-- Omni News HTML邮件模板,参考自cclank开源项目 -->
<div style="max-width:600px;margin:0 auto;font-family:-apple-system,sans-serif">
<h1 style="color:#1a1a1a;border-bottom:3px solid #0066cc;padding-bottom:10px">
📰 Omni News 日报
The architecture section explicitly states the sentiment layer is '中文情感分析', and elsewhere the skill consistently specifies Chinese-only sentiment tooling and Chinese-oriented output without offering a language choice. This creates a natural-language locale policy issue because users seeking multilingual or English news handling are not given an opt-in or alternative.
The skill claims push/monitoring behavior was removed, but later sections still describe push rules, personalized tracking, and monitoring as active capabilities. This kind of contradictory documentation is dangerous because operators or downstream agents may enable data collection, retention, or outbound notifications that users were told were disabled, creating privacy and scope-creep risk.
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
Although the file says TrendRadar was removed, substantial later content still presents TrendRadar-derived tracking, report generation, monitoring, and smart push features as integrated behavior. In a skill document, this discrepancy can mislead an agent into performing persistent surveillance-style actions or retaining topic profiles beyond the user's expectation, which increases privacy and consent risk.
No suspicious patterns detected.