ClawHub
Back to skill

Security audit

Trading Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language trading strategy education and backtesting skill with no hidden code, persistence, credential use, or automatic trading behavior.

Install this only if you want Chinese-language help with trading strategy education or backtesting. Treat outputs as educational analysis, verify any generated Python before running it, and do not rely on the skill for regulated investment advice, live trading execution, or guaranteed financial outcomes.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill advertises very broad capabilities across strategy development, education, backtesting, risk management, chart analysis, and multiple markets without clear invocation boundaries. This can cause ambiguous or overly eager activation, increasing the chance the agent applies the skill in unintended contexts such as personalized financial guidance or unsupported market-specific advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill metadata and body are primarily in Chinese and do not indicate whether other languages are supported, which can cause mismatches between user intent and skill behavior. In an agent-routing context, this may trigger the skill for users who cannot understand its outputs or constraints, reducing transparency around financial-risk-related guidance.

Content

No source excerpt is available for this finding.