Security audit
Security checks for vulnerabilities and agentic risk
This skill fetches public trending-topic data from named Chinese platforms and does not show hidden credential use, persistence, destructive behavior, or exfiltration beyond the disclosed trend lookups.
Install this only if you are comfortable with the agent running a local Python script that contacts Zhihu, Weibo, Baidu, and Bilibili to fetch public trend data. Review the broad trigger phrases if you want tighter control over when network requests occur.
The trigger phrases are broad, generic requests like '今天什么热点' and '帮我看看热搜', which can overlap with ordinary user intent and cause the skill to activate unexpectedly. In an agent environment, overbroad invocation increases the chance of unintended data access, network calls, or workflow chaining without the user clearly selecting this specific skill.
The skill clearly instructs the agent to run a network-capable script against multiple external platforms, but the manifest does not declare any tool scope or allowed-tools boundary. This creates an authorization and transparency gap: an agent or host may permit broader network access than users expect, and reviewers cannot verify the intended outbound capability from the manifest alone.
The trigger phrase '今天什么热点' is broad and overlaps with ordinary conversation, which can cause the skill to activate unexpectedly. In this skill's context, accidental activation can initiate real-time network requests to multiple third-party platforms without the user explicitly asking for external retrieval.
This Python file includes its top-level description, CLI help text examples, and later user-facing console output in Chinese only. That creates a natural-language locale constraint without presenting the user with any language selection or documenting a justified region-specific limitation.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
def fetch_zhihu(limit=20):
"""抓取知乎热榜"""
url = "https://api.zhihu.com/topstory/hot-lists/total?limit={}".format(limit)
try:
req = Request(url, headers=HEADERS)
with _urlopen(req, timeout=10) as resp:
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
def fetch_bilibili(limit=20):
"""抓取B站排行榜"""
url = "https://api.bilibili.com/x/web-interface/ranking/v2?rid=0&type=all"
try:
req = Request(url, headers=HEADERS)
with _urlopen(req, timeout=10) as resp:
The README presents the skill entirely in Chinese and the trigger phrases are also Chinese-only, which indicates a fixed language expectation. There is no stated user opt-in, multilingual option, or justification that the skill is intentionally limited to a Chinese-language or China-region audience.
文件标题、说明、示例触发语和使用方式均默认要求中文交互，没有提供用户语言偏好选择，也未声明这是仅面向中文环境的区域性技能。根据语言/locale 政策，若限定特定语言，通常应提供显式选择或合理、清晰的约束说明。
The documentation describes real-time scraping of several external platforms but does not clearly warn the user that using the skill will contact third-party services. This weakens informed consent and can surprise users in environments where network activity, privacy, or compliance constraints matter.
The manifest repeatedly states the skill's purpose is limited to collecting and returning structured hotspot data, with no additional analysis or publishing behavior. However, the file ends with branding, a website URL, and a call-to-action link for an external diagnosis service, which is outside the stated scope of a trend aggregation skill.
No suspicious patterns detected.