ClawHub
Back to skill

Security audit

Xuxiaoming

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese A-share technical analysis persona skill; its main issue is financial-risk framing, not hidden or unsafe system behavior.

Install only if you want a Chinese-language A-share technical-analysis persona. Treat its market framework as educational commentary, not personalized financial advice; trading can lose money, and users should make their own decisions or consult a qualified professional for personal investment guidance.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill provides structured trading heuristics, position-sizing guidance, and market-timing style instructions, but does not include an explicit warning that financial markets involve risk and losses may occur. In context, users may treat the persona-framed analysis as actionable advice, increasing the chance of harmful reliance without understanding uncertainty, suitability, or downside risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill strongly constrains the assistant to a fixed Chinese-language persona and response style without offering a user language choice or accessibility fallback. While not a classic security flaw, this can cause misunderstanding of financial content, reduce user comprehension, and make risk disclosures less effective for users who are not comfortable with the imposed language/persona.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.