ClawHub
Back to skill

Security audit

Trading Agents多智能体量化交易

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language informational trading guidance skill; it has financial-risk content but no code, credential access, persistence, or automatic trading behavior.

Install only if you want Chinese-language AI trading education and platform/strategy prompts. Treat outputs as informational, verify financial claims independently, use simulated accounts before real trading, and do not let any agent place trades or connect brokerage credentials without explicit review.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is written entirely in Chinese and does not provide a language-choice mechanism or warn that activation will switch languages. This can cause users to receive instructions they may not fully understand, increasing the chance of misunderstanding trading, risk, or compliance guidance. The surrounding content includes financial workflows and strategy suggestions, so language ambiguity makes mistakes more consequential than in a low-risk domain.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger examples are broad natural-language phrases such as asking what Trading Agents is, how to do AI quantitative trading, what platform beginners should use, or asking for stock picking help. These overlap heavily with ordinary investment questions, so the skill may activate unexpectedly and steer users into detailed trading guidance or platform recommendations without clear opt-in. In a finance context, overbroad invocation is more sensitive because it can influence risky real-world financial behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.