ClawHub
Back to skill

Security audit

CashFlow Lite: Self-Sustaining AI Agent

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is not malicious, but it broadly encourages autonomous money-making execution without clear approval gates or limits.

Install only if you will keep the agent on analysis and planning by default. Require explicit human approval before spending money, posting or messaging, using accounts, contacting third parties, signing up for services, or taking any external action.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The opening description says the agent 'finds and executes money-making opportunities with minimal cost,' which frames autonomous execution of potentially financial actions but provides no safety warnings or operational limits. In this context, the combination of profit-seeking and execution language increases the risk of fraud, spam, policy abuse, unauthorized spending, or other harmful real-world actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README tells users to 'give your agent a goal and let it work' without defining scope, approval gates, or prohibited actions. In a skill explicitly focused on finding and executing money-making opportunities, this broad invocation guidance can encourage autonomous financial or policy-violating behavior with little operator oversight.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.