ClawHub
Back to skill

Security audit

每日新闻日报 v2.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward daily news report generator that uses web search and saves a dated report, with its automation and storage behavior disclosed.

Install this if you want an automated Chinese daily news digest. Be aware it may run on the disclosed weekday schedule, perform web searches, and keep dated Markdown report archives in memory.

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)

Skill Enumeration

Medium
Category
Agent Snooping
Content
| 文件 | 状态 | 说明 |
|------|------|------|
| `skills/daily-news/SKILL.md` | ✅ 当前 | 本技能文档 |
| `daily_news_query.py` | ⚠️ 已废弃 | 旧版 Bing 爬虫方案 |
| `daily_news_tavily.py` | ⚠️ 已废弃 | 旧版 Tavily API 方案 |
| `memory/daily_news_*.md` | ✅ 历史存档 | 每日报告存档 |
Confidence
80% confidence
Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The skill metadata and main instructions are primarily written in Chinese, with a few English trigger phrases, but nowhere does it state that users may choose their preferred language or locale. Under the policy rule, forcing a specific language or locale without user opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.