ClawHub
Back to skill

Security audit

Daily Hot Ai News 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This is a simple user-triggered AI news briefing skill that uses web search and does not request local access, credentials, persistence, or execution authority.

Install this if you want a Chinese AI-news briefing helper. Be aware that its routing rules are broad enough that it may run for some vague AI 'recently' questions, so users should phrase non-news AI questions clearly when they do not want current-events search.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill advertises broad trigger phrases like '今天AI有什么新闻' and similar everyday wording without explicit exclusion boundaries, which can cause the agent to invoke this skill for general AI discussion rather than clear news requests. Over-broad routing is dangerous because it can lead to unintended web searches, irrelevant tool use, and increased exposure to untrusted external content when the user did not actually ask for news aggregation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The semantic matching logic is ambiguous because it activates whenever a message contains an AI-related term plus a broad intent term like '最近' or '发生了什么', which are common in many non-news contexts. In this skill, that ambiguity is more risky because activation triggers WebSearch across multiple external sources, expanding attack surface and making the agent more likely to retrieve and summarize untrusted or irrelevant content unnecessarily.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.