ClawHub
Back to skill

Security audit

Ltv Cac Calculator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward LTV/CAC calculation helper with no hidden execution, persistence, or data access; the main caveat is that most instructions are in Chinese.

Install only if you are comfortable reviewing the Chinese prompts and financial assumptions. Treat the output as decision support, not a definitive budget recommendation, and verify sensitive LTV/CAC inputs before acting on the results.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

Medium
Confidence
95% confidence
Finding
The skill content is primarily in Chinese and instructs a fixed interaction flow without offering the user a language choice. This can cause miscommunication, incorrect interpretation of financial inputs or outputs, and exclusion of users who cannot reliably review the assumptions used in the LTV/CAC calculation. In a financial decision-support skill, ambiguity around assumptions and results increases operational risk even if it is not directly exploitable as code execution or data exfiltration.

Static analysis

No suspicious patterns detected.