ClawHub
Back to skill

Security audit

A-Share Claw (A股龙虾)

Security checks for vulnerabilities and agentic risk

Overview

This skill describes a disclosed paper-trading automation workflow with expected file updates and scheduled runs, with no evidence of hidden or malicious behavior.

Before installing, confirm where the scheduled jobs will be created, how to disable them, and whether README updates should be allowed. Use an MX API key intended for paper trading only, and review generated workspace scripts before running them.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs writing a review JSON file and updating the workspace README, but it does not warn the user that it will modify local files or require confirmation before doing so. This creates a transparency and consent issue: an agent following the skill could make persistent changes to the user's workspace unexpectedly, which is especially relevant in an automation workflow that may run on a schedule.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.