ClawHub
Back to skill

Security audit

6大平台热搜聚合

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public Chinese trending-topic lists and prints them locally, with no evidence of hidden persistence, credential use, destructive behavior, or unrelated data collection.

Install only if you want a Chinese-platform trend aggregator that makes live requests to Zhihu, Weibo, Baidu, Bilibili, Douyin, and Toutiao. Be aware that short trend-related prompts may activate it, but the reviewed artifacts show only public data fetching and local output.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (8)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The skill description states the capability entirely in Chinese and presents the skill as a Chinese-platform aggregation tool, but does not explicitly offer a language choice or explain that the locale restriction is intentional and region-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill advertises and demonstrates network-capable behavior by calling external trend APIs, but it does not declare any tool scope such as permissions or allowed-tools. This creates an authorization and transparency gap: the runtime may permit network access without users or reviewers being clearly informed which external domains or capabilities the skill is expected to use.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The phrase “中文优先” indicates a language preference is imposed by default in the skill description. There is no accompanying language-choice mechanism or opt-in language selection documented in the file.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrases are broad and map to common conversational words like '热点', '趋势', and '什么火', increasing the chance that the skill activates unexpectedly in unrelated contexts. Unintended invocation can cause surprise network requests, incorrect routing away from the user's real intent, and unnecessary disclosure of user prompts to external services if downstream processing occurs.

External Transmission

Medium
Category
Data Exfiltration
Content
def fetch_zhihu(limit=10):
    """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:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
def fetch_bilibili(limit=10):
    """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:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Description-Behavior Mismatch

Low
Confidence
92% confidence
Finding
The manifest describes a skill for aggregating trending lists across six Chinese platforms, which matches the fetch logic. However, both the module docstring and runtime flags add a separate capability for 'AI选题推荐' and suggest downstream content generation workflows, which goes beyond simple aggregation.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The HTTP headers hard-code `Accept-Language` to prefer `zh-CN`, which imposes a specific locale behavior on all requests. There is no user opt-in, configuration option, or documented region-specific justification in the file, so this is a natural-language locale policy concern.

Static analysis

No suspicious patterns detected.