ClawHub
Back to skill

Security audit

热点收集雷达

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a real hotspot-scraping/reporting tool, but it needs Review because it can contact disabled platforms and can use local credentials for hardcoded Feishu/Instagram flows.

Install only if you are comfortable with a broad web-scraping tool that stores local archives and may use local Feishu or Instagram credentials. Before running, review and fix the platform enablement logic, replace hardcoded Feishu recipient/app IDs with your own configuration, avoid plaintext Instagram session cookies, and do not send authenticated traffic through an untrusted proxy.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tainted flow: 'proxies' from os.environ.get (line 29, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Content
'Accept': 'application/json, text/plain, */*',
    }
    proxies = PROXIES if use_proxy else None
    r = requests.get(url, headers=headers, timeout=timeout, proxies=proxies)
    r.raise_for_status()
    if json_resp:
        return r.json()
Confidence
96% confidence
Finding
r = requests.get(url, headers=headers, timeout=timeout, proxies=proxies)

Tainted flow: 'app_js' from requests.get (line 9, network input) → requests.get (network output)

Medium
Category
Data Flow
Content
app_js = [j for j in js_files if 'app' in j.lower()][0]
print(f'App JS: {app_js}')

j = requests.get(app_js, timeout=10)
text = j.text

# 找所有 URL 或路径字符串
Confidence
92% confidence
Finding
j = requests.get(app_js, timeout=10)

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
The function claims to crawl only enabled platforms, but actually submits jobs for all platforms regardless of configuration. This can cause unexpected outbound connections to many third-party services, undermining user intent, policy controls, and any attempt to limit data exposure or network reach.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill documentation states that raw data and generated reports are stored locally under dated files, but it does not clearly warn users that execution creates persistent local artifacts. This can expose scraped content, keywords, and analysis history to other local users or later processes, especially on shared machines or managed agent environments.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises Feishu push/sync features but does not clearly warn that report contents may be transmitted to an external third-party service. If reports contain sensitive monitored keywords, competitive intelligence, or internal analysis, sending them externally without explicit user consent can cause unintended data disclosure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The code reads an Instagram session cookie from local config and sends it in an authenticated request to Instagram, potentially through a proxy when use_proxy=True. Session cookies are highly sensitive credentials; transmitting them without strong safeguards, clear consent, and proxy restrictions creates account-takeover and privacy risks if intercepted or misused.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.