ClawHub
Back to skill

Security audit

虾皮市场风格轮动分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent A-share market-style analysis helper, with expected external API and token setup instructions disclosed.

Before installing, make sure you trust the DaxiAPI CLI package and avoid putting your token in shared chats, logs, repositories, backups, or synced dotfiles. Prefer a temporary environment variable when practical, and delete or rotate the token if it is exposed.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list contains broad, common financial terms such as '沪深300', '中证2000', and '大盘股小盘股' that can match many user requests outside the skill's narrow purpose. This can cause unintended invocation, leading the agent to apply style-rotation guidance in contexts where the user wanted general market information, increasing the risk of irrelevant or misleading financial analysis.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The document advises persisting an API token in shell startup files and a CLI config file, which typically stores the credential in plaintext on disk. While this is common operational guidance, failing to explicitly warn about plaintext-at-rest risks can lead to token exposure through local compromise, backups, dotfile sync, or accidental sharing.

Static analysis

No suspicious patterns detected.