ClawHub
Back to skill

Security audit

simple-ledger

Security checks across malware telemetry and agentic risk

Overview

This is a local personal-finance ledger with disclosed file writes and optional market quote lookups; I found no hidden upload, credential access, or unsafe persistence.

Install only if you are comfortable storing personal finance data as local plain-text CSV/JSON files. Back up the ledger directory before using delete, remove, overwrite, or cost-edit commands. Leave AUTO_REFRESH disabled if you want every network quote lookup to be an explicit per-command choice.

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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The guide documents a delete command for financial goals without any warning that it is destructive, reversible status, or confirmation behavior. In a finance-related skill using plain-text local storage, users may accidentally delete savings goals and associated planning context, causing data loss and misleading downstream budgeting or progress predictions.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The documentation describes a persistent auto-refresh mode via a `.env` setting that causes portfolio and summary commands to fetch live quotes automatically, while emphasizing explicit confirmation for one-off `--allow-network` actions. This creates an inconsistency in consent semantics: users may believe network access is always gated per command, but a prior config change can silently re-enable outbound requests and ongoing data disclosure.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.