ClawHub
Back to skill

Security audit

9527-github-trending

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public GitHub Trending data and optionally sends it to user-configured notification channels, with no hidden persistence or unrelated data access found.

Before installing, confirm you are comfortable sending GitHub Trending summaries to the notification service you configure. Store Telegram tokens, chat IDs, and webhook URLs securely, avoid putting real secrets directly in shell history or cron entries, and verify the destination channel before scheduling automatic pushes.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
This markdown file describes sending results to Telegram, 钉钉, and 企业微信 using bot tokens and webhook URLs, but it does not warn users that repository/trending data will be transmitted to external services or that these credentials are sensitive. Under the markdown-specific warning rule, networked push behavior and secret-bearing parameters should be accompanied by a user-facing caution about privacy and credential handling.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The natural-language content forces a single language presentation for the skill documentation, and there is no indication that the skill is intended only for a Chinese-speaking or region-specific audience. The policy allows locale constraints when they are justified or optional, but neither condition is documented here.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill description and examples show sending data to Telegram, 钉钉, and 企业微信, including use of bot tokens, chat IDs, and webhook URLs, but provide no user-facing warning about transmitting content to third-party services or safeguarding those secrets. For a markdown file, this is a missing warning about behavior that can affect privacy or system integrity.

Natural-Language Policy Violations

Low
Confidence
73% confidence
Finding
The natural-language content of the skill is entirely in Chinese, and there is no indication that users can select another language or that the skill is intentionally limited to a Chinese-speaking audience. This can constitute a language/locale policy issue when a skill implicitly forces a specific language without opt-in.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The module description is written entirely in Chinese and does not indicate that users can choose another language or locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy issue even when it appears in comments, docstrings, or user-facing help text.

External Transmission

Medium
Category
Data Exfiltration
Content
def send_telegram(message: str, token: str, chat_id: str) -> bool:
    """发送到 Telegram"""
    url = f"https://api.telegram.org/bot{token}/sendMessage"
    data = {
        'chat_id': chat_id,
        'text': message,
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.