ClawHub
Back to skill

Security audit

AI新闻早报（中文版）

Security checks across malware telemetry and agentic risk

Overview

This skill coherently generates AI news briefings using disclosed search tools and an optional daily schedule, with no evidence of hidden exfiltration or destructive behavior.

Install only if you want an agent to perform outbound news searches and possibly spend Tavily API quota. Store the Tavily key carefully, verify the package slug before installing, and enable the cron job or run_daily.sh only if you want automatic daily execution; review the hardcoded local proxy in run_daily.sh first.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manual trigger phrases are very broad, natural-language requests such as '生成今天的AI日报' and '帮我搜一下今天AI圈有什么大事', which can plausibly appear in ordinary conversation and unintentionally activate the skill. In an agent environment, ambiguous activation can cause unexpected web searches, outbound API calls, and generation behavior without clear user intent, especially because the skill performs external fetching and synthesis.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The guide tells users to place the Tavily API key directly into ~/.openclaw/.env or ~/.openclaw/openclaw.json but does not warn that these files contain sensitive credentials or recommend access restrictions, rotation, or secret-management practices. If those files are world-readable, accidentally committed, shared in support logs, or exposed by another local compromise, the API key can be stolen and abused for unauthorized API usage.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.