ClawHub
Back to skill

Security audit

A股市场研究助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed A-share market research template that guides financial analysis and report generation without hidden code, persistence, credential access, or account-changing actions.

Install this only if you want a Chinese-language A-share industry research workflow. Review any generated target prices, upside estimates, and stock screens independently, verify source dates and market data freshness, and avoid treating the output as personalized investment 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
  • 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
95% confidence
Finding

The trigger list is broad and contains common finance-related phrases such as '市场研究', '行业动态', and '投资主题', which can cause the skill to activate in routine conversations that were not intended to request this specialized workflow. In this context, unintended invocation is more concerning because the skill produces investment-research outputs and stock screening, including recommendations framed around '50%以上上涨空间', which could steer users into actionable financial content without clear intent or appropriate gating.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Nearly all user-facing instructions, examples, and output specifications are written in Chinese and oriented to Chinese-language interaction, but the file does not state that language selection is optional. Under the policy, forcing a specific language without opt-in is a natural-language locale constraint that should be documented or made selectable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.