ClawHub
Back to skill

Security audit

Finance Data Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed educational financial-data-analysis skill with no executable code, tool access, credential handling, persistence, or hidden behavior.

Install this only if you want methodology and templates for financial-institution operating and financial analysis, especially in a Mainland China regulatory context. Do not treat its sample SQL/Python as production-ready, and keep using your institution's approval, desensitization, retention, and review processes before applying outputs to real data or 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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The statement says the skill is '以中文为主' and aligned to '中国内地持牌金融机构', while also stating it does not cover overseas regulatory standards. This is a natural-language locale constraint that does not present an explicit opt-in or alternative language/locale path for users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.