ClawHub
Back to skill

Security audit

虾皮市场热股分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent A-share stock-analysis helper, with the main caution being how it asks users to store a Daxi API token.

Install only if you trust the Daxi API service and the daxiapi-cli npm package. Use a dedicated revocable token, prefer temporary environment variables or a credential manager on shared machines, avoid pasting real tokens into chats or logs, and treat the generated stock report as informational rather than investment advice.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The document instructs users to append a long-lived API token directly into a shell startup file, which persistently exposes the secret to anyone with access to the user profile and can also encourage unsafe handling practices on shared systems. While it is standard operational guidance rather than overtly malicious behavior, the nearby text does not clearly warn about risks such as local file disclosure, backups, dotfile syncing, or multi-user access.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The Windows example uses persistent environment-variable storage for the API token without warning that the secret may remain accessible to other local processes, user profile exports, or anyone with access to the account or machine. In a skill that requires authentication to a market-data API, this increases the chance of credential leakage and unauthorized API usage, especially on shared or managed endpoints.

Static analysis

No suspicious patterns detected.