ClawHub
Back to skill

Security audit

每日综合新闻（基于news-aggregator-skill并发送至飞书文档）

Security checks across malware telemetry and agentic risk

Overview

This is a coherent daily news briefing skill, with expected network fetching, local report output, and optional Feishu document creation.

Before installing, verify that the referenced news-aggregator-skill is trusted, do not use the listed proxy unless it is yours or trusted, and require confirmation before saving reports or creating any Feishu document.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad, generic news-related utterances that could plausibly appear in normal conversation and unintentionally activate the skill. Because this skill performs network access, fetches external content, and writes reports to disk, accidental invocation can cause unwanted side effects beyond a simple conversational response.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly saves generated reports to a dated directory on disk but does not warn users about this persistent side effect. Silent file creation can surprise users, consume storage, and create privacy or integrity issues if the report contains sensitive prompts, fetched content, or is written in shared environments.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The optional Feishu document creation introduces an external data transfer and content publication step, but the skill does not warn users about privacy, integrity, or authorization implications. If invoked unintentionally or used with sensitive content, it could publish information to third-party systems or overwrite/shared documents without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.