ClawHub
Back to skill

Security audit

AI 热点工作台

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward AI news collection and briefing workflow with one disclosed, optional insecure TLS debug flag that users should normally avoid.

Install only if you want a workflow that gathers public AI news and prepares a Chinese briefing. Use the default command with TLS verification enabled; avoid --insecure except for temporary local certificate troubleshooting because it can allow tampered feed content on an untrusted network.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The --insecure flag causes urllib to use an unverified SSL context, disabling certificate validation for all configured remote RSS/Atom feeds. If this option is used in a real workflow, a network attacker or hostile proxy could intercept HTTPS traffic and supply tampered feed content, causing the agent to ingest and forward manipulated news items.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.insecure_tls_verification

HTTPS certificate verification is disabled.

Warn
Code
suspicious.insecure_tls_verification
Location
scripts/collect_ai_hot_news.py:230