Back to skill

Security audit

bookkeeping-cleanup

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a controlled bookkeeping workflow and a local notes checker, whose results do not prove that the books are reconciled.

Use this as a checklist with agent-assisted bookkeeping review. Independently verify balances, duplicates and unresolved entries against statements; the notes checker cannot establish correctness or completeness. Approve journal entries individually. The separate unsigned Windows app is unnecessary for this workflow and requires its own security review.

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
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code checks only text formatting and substring presence. Labels such as 'Uncategorized' and 'Duplicates' satisfy its checks without any examination of ledger transactions. Its report lists document-lint problems, not bookkeeping discrepancies. This is a materially different primary purpose from the declared ledger cleanup and reconciliation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
81% confidence
Finding

The command appears to validate checklist notes, which is materially narrower than performing the advertised bookkeeping operations. YAML input and local output are not themselves problematic implementation details; the mismatch concerns the apparent primary function. Confidence is limited because the invoked Python script's implementation was not supplied.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The implementation checks document formatting rather than reconciling ledger accounts or identifying outstanding transactions.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

The manifest promises account reconciliation and a complete list of uncategorized or duplicate ledger entries. This implementation only searches input text for section names, excessive line lengths, and banned phrases; its 'No problems found' result does not establish that any ledger entries were examined or reconciled.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.