ClawHub
Back to skill

Security audit

虾皮SQL自由选股

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed stock-screening helper that queries a third-party DAXIAPI service and does not show hidden, destructive, or unrelated behavior.

Install this only if you intend to use DAXIAPI for A-share stock screening, trust the daxiapi-cli npm package, and are comfortable storing or providing a DAXIAPI token locally. Because the trigger wording is broad, confirm the agent is about to run the stock-screening CLI before allowing API calls, and treat generated stock analysis as informational rather than financial advice.

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
88% confidence
Finding
The trigger phrase "选股" is extremely broad and can match many ordinary investing queries that do not require this SQL-based skill. That increases the chance of unintended invocation, causing the agent to enter a workflow that solicits token setup or performs external CLI/API actions when the user only asked for general stock discussion.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The listed trigger phrases include generic screening terms like "选股", "股票筛选", and similar broad language without strong scope constraints. In context, this is more dangerous because the skill's process includes external command execution and credential configuration steps, so accidental routing can lead to unnecessary token prompts, external API use, or user confusion.

Static analysis

No suspicious patterns detected.