ClawHub
Back to skill

Security audit

Accounting

Security checks for vulnerabilities and agentic risk

Overview

This is a local accounting assistant skill that stores and edits user-entered financial records locally, with no evidence of hidden execution, network access, credential use, or deceptive behavior.

Before installing, decide where the local accounting data directory should live, back it up separately if the records matter, and review update or delete requests carefully because they modify stored financial records.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly supports updating and deleting accounting records and stores data in local JSON files with rotating backups, but it does not clearly warn that edits or deletions can alter financial history and may not be easily recoverable beyond the retained backups. In an accounting context, silent modification or deletion of records can cause loss of integrity, user confusion, and financial reporting errors even without malicious code execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language policy review applies to all file types, including markdown. The usage examples repeatedly frame inputs in yuan, which can imply a forced locale/currency convention unless the skill is explicitly region-specific or allows user selection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.