ClawHub
Back to skill

Security audit

A股基本面筛选

Security checks for vulnerabilities and agentic risk

Overview

This is a simple A-share fundamental screening skill with no executable code, persistence, credential access, or account-changing behavior.

Before installing, treat the screening thresholds as a quick filter only. Confirm any financial data and risks from reliable sources, and do not rely on this skill alone for buy, sell, or trading decisions.

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
Confidence
95% confidence
Finding
The trigger phrases are broad enough to match ordinary investing questions such as whether a stock is good, risky, or buyable, which can cause the skill to activate outside a clearly bounded user intent. In an investment context, ambiguous activation is more dangerous because it may inject simplified screening logic into general financial advice conversations without the user explicitly requesting this specific methodology.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
The file presents all user-facing natural-language content exclusively in Chinese, which can amount to a language policy constraint if users are not given an opt-in choice. There is no explicit statement that the skill is China-region specific or that Chinese is required for compliance or user preference.

Static analysis

No suspicious patterns detected.