ClawHub
Back to skill

Security audit

liyan de skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed gold-investment analysis skill that uses web search for market data and does not install code, persist itself, access credentials, or mutate user accounts.

Install only if you want a Chinese-language gold market analysis workflow that searches current market data and summarizes ETF options. Verify prices and fund details with official market or fund sources before making investment decisions, and do not treat its output as personalized financial advice.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill declares that it must be used for essentially any gold-investment-related query, creating an overly broad trigger scope and mandatory invocation path. This can override normal agent discretion, route users into a specialized workflow even when unnecessary, and increase the chance of inappropriate tool use, stale financial advice, or failure to honor user intent and broader safety/policy constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Forcing a fixed Chinese output style without regard to the user's language can cause the system to ignore explicit user preferences and degrade transparency or comprehension. In a financial-analysis skill, that creates a meaningful safety risk because users may misunderstand recommendations, risk disclosures, or caveats if the response language does not match their needs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.