ClawHub
Back to skill

Security audit

chundengtai-v3

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only A-share trading assistant, but it gives prescriptive buy, sell, stop-loss, and position-sizing guidance without adequate risk framing or user opt-in controls.

Review this carefully before installing. It does not appear to contain malware or hidden execution, but it may cause an agent to provide decisive short-term trading instructions. Treat its outputs as market commentary only, confirm data freshness, and do not rely on it for personalized investment decisions.

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
  • 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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill provides specific entry, exit, stop-loss, position-sizing, and timing rules that amount to actionable investment advice, but it does not present a clear financial-risk warning or state that outputs are not personalized investment advice. This is especially dangerous because the skill frames the guidance as direct numeric conclusions and concrete sell rules, which can encourage users to act without understanding market, suitability, or loss risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger scope is broad enough that ordinary requests about analyzing, diagnosing, or selecting A-shares could invoke the skill unintentionally. In a financial-advice context, unintended activation is risky because it may cause the agent to deliver prescriptive trading guidance when the user did not explicitly request this specific strategy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The output specification mandates a fixed formatting and Chinese-language presentation style, including rigid wording constraints, without offering the user a language or locale preference. This can violate language/locale choice expectations when the skill is used in a broader multilingual environment.

Content

No source excerpt is available for this finding.