ClawHub
Back to skill

Security audit

investoday-stock-market-broadcast

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed A-share market broadcast helper that uses public market data and does not show hidden code execution, persistence, or private data handling.

Before installing, be aware that generic Chinese market questions may activate this skill and cause it to fetch current public market data. Treat its output as time-sensitive commentary, not investment advice.

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
95% confidence
Finding
The trigger list is broad and includes common conversational phrases like '市场怎么样' and '盘面总结', which can cause the skill to activate when a user is making general market small talk rather than explicitly requesting this capability. In an agentic system, unintended invocation can route queries to the wrong toolchain, causing irrelevant external data fetches and misleading financial commentary.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation scenarios are phrased as broad intents ('当前市场怎么样', '热点在哪', '快速理解市场情绪') without clear selection boundaries versus adjacent finance skills. This increases the chance of over-selection, where the skill is chosen for loosely related requests and produces authoritative-seeming market summaries from external data the user may not have intended to invoke.

Static analysis

No suspicious patterns detected.