ClawHub
Back to skill

Security audit

13-Week Cash Flow Forecast

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only finance modeling skill that asks for relevant business cash-flow inputs and does not include code execution, persistence, hidden behavior, or automatic data access.

Installers should expect this skill to work with sensitive company financial information that the user provides, such as cash balances, AR/AP aging, payroll, debt, and covenant data. Use it when you intentionally want a 13-week liquidity forecast, and avoid sharing unnecessary confidential details in generic budgeting or finance chats.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes broad phrases such as short-term liquidity questions and generic cash-management requests that can match ordinary finance conversations beyond a deliberate request for this specific skill. This creates unintended invocation risk, which can cause the agent to activate the skill in the wrong context and produce inappropriate or confusing outputs, though it does not directly enable code execution or data exfiltration.

Static analysis

No suspicious patterns detected.