Back to skill

Security audit

六维共振量化助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language A-share stock analysis framework with financial-risk caveats and no code, persistence, credential access, or hidden execution behavior.

Use this only as an educational analysis aid for Chinese A-share investing. Verify market data independently, treat buy/sell and position suggestions as non-professional opinions, and avoid relying on it where regulated financial advice or another language is required.

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
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
93% confidence
Finding

The trigger description covers a very broad set of common investment-analysis phrases, making the skill likely to activate for many generic finance requests even when the user did not explicitly ask for this specific framework. Over-broad invocation can cause inappropriate routing, crowd out safer or more suitable skills, and increase the chance the agent delivers regulated or high-risk financial guidance in contexts that only asked for general information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written entirely in Chinese and implies Chinese-language operation without offering locale selection or fallback behavior. This can lead to user confusion, misinterpretation of financial risk disclosures, and incorrect use when the surrounding conversation is in another language, which is especially problematic in an investment context where nuance matters.

Content

No source excerpt is available for this finding.