ClawHub
Back to skill

Security audit

Worth It — Agent Profitability Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small profitability-logging prompt that sends explicit value-log commands to a local API, with privacy considerations but no hidden or destructive behavior in the artifact.

Install this only if you intend your agent to log $saved, $earned, $time, and $cost entries to a local Worth It service. Avoid putting sensitive client names, confidential project details, or private financial context in the free-text description unless you are comfortable storing it in that local dashboard.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs agents to recognize patterns anywhere in user messages and send the extracted contents to a local HTTP API, but it provides no privacy notice, consent boundary, or limitation on what may be transmitted. Because commands are detected in free-form conversation, users may unintentionally include sensitive project names, financial data, or other confidential text that will be forwarded off-model to another service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.