ClawHub
Back to skill

Security audit

Bank Financial Report

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only financial report analysis skill with appropriate warnings; the main caution is broad activation on finance or valuation prompts.

Before installing, treat this as a conversational financial analysis aid, not an approval, audit, lending, or investment decision system. Provide only summarized, necessary financial data, avoid pasting confidential originals or detailed customer/supplier lists, verify current regulatory facts independently, and require qualified human review before using outputs in credit or investment workflows.

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 at line 10 ("财务分析") is broad enough to match many ordinary finance-help requests, not just bank-grade financial statement analysis. This can cause unintended activation of a specialized skill that encourages users to paste sensitive corporate financial data, increasing the chance of over-collection, context confusion, and inappropriate use in higher-risk credit or investment workflows.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger at line 16 ("估值分析") is also broader than the stated scope and can activate for general valuation or investing questions unrelated to financial-report analysis. In this skill's context, accidental invocation is more concerning because the content discusses credit, fraud screening, ratings, and investment thesis generation, which may lead users to rely on specialized outputs without the intended contextual checks.

Static analysis

No suspicious patterns detected.