ClawHub
Back to skill

Security audit

hot-it-news

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed news-fetching helper that opens three public Chinese tech/product sites and formats their homepage hot articles.

Installers should know this skill may run for broad tech-news prompts and will open three named external websites in a visible browser. It does not request credentials or local private data, but users wanting narrower behavior should trigger it only for those specific sites or homepage hot/recommended articles.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description includes very broad trigger phrases covering generic IT, tech, internet, AI, product, business-tech, and 'hot news' requests. This can cause the skill to activate for a wide range of common queries, increasing the chance it overrides more appropriate skills and forces unnecessary browser-driven navigation to external sites. In context, this broad routing is risky because the skill mandates headed browsing and strict execution flow against third-party sites, so over-triggering expands exposure and may degrade safety and reliability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.