ClawHub
Back to skill

Security audit

金融知识问答

Security checks for vulnerabilities and agentic risk

Overview

This finance skill is not malicious, but it asks for broad execution/data access while offering personalized investment guidance without clear user safeguards.

Review before installing. Use this only for educational A股 analysis or tightly scoped data tasks, avoid giving it brokerage credentials or sensitive trading history unless you explicitly intend that use, and require confirmation before any command execution or API-key-backed data access. Treat its outputs as informational, not professional financial advice.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The document makes strong safety claims such as removing risky code and cleaning external dependencies, yet it also declares `exec` capability, external A股 data sources, and API key usage. This mismatch can mislead users and agents into granting trust or permissions under false assumptions, increasing the chance of unsafe execution or network access.

Intent-Code Divergence

Medium
Confidence
90% confidence
Finding
The file labels itself as usable as pure markdown while simultaneously documenting command-execution failure modes such as permission issues, command failures, and process timeouts. That inconsistency can cause an agent or user to underestimate the operational impact of enabling the skill and approve execution in contexts where only non-executing behavior was expected.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation text says to use the skill whenever the user needs finance knowledge Q&A, which is broad enough to match many generic finance requests. In a finance context, over-broad routing is risky because the skill also discusses investment advice, user data handling, API keys, and execution capability, so accidental invocation could expose users to inappropriate automation or sensitive-data processing.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill describes handling user data, generating personalized investment advice, using API keys, and having executable capability, but it does not present a clear user-facing warning about privacy, financial harm, or system-impacting actions. In a financial skill, this omission is especially dangerous because users may treat outputs as safe or compliant advice and may not understand that secrets, personal data, or local system actions could be involved.

Static analysis

No suspicious patterns detected.