ClawHub
Back to skill

Security audit

investoday-stock-news-event-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed finance-news analysis workflow that fetches public market data through a named Investoday API dependency and does not show hidden storage, persistence, or destructive behavior.

Install this if you want an Investoday-backed A-share news/event analysis helper and are comfortable providing an INVESTODAY_API_KEY. Review usage when a query could instead be about intraday price movement, a single news item, or analyst reports, because the triggers are somewhat broad.

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
Confidence
92% confidence
Finding
The trigger list is very broad and consists of common finance phrases such as '最近新闻', '消息面', '利好利空', and '风险消息', which are likely to appear in ordinary portfolio or market discussions. This can cause the skill to be invoked unintentionally, routing users into a data-fetching workflow they did not explicitly request and increasing the chance of incorrect tool selection or unnecessary external API use.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation scenarios overlap substantially with nearby finance workflows like '今天为什么涨跌', '某一条消息怎么解读', and '机构近期怎么看', but the boundaries are only described informally. In practice, this ambiguity can lead an agent to invoke the wrong skill, producing misleading analysis or over-collecting external data when a narrower skill would be more appropriate.

Static analysis

No suspicious patterns detected.