Back to skill

Security audit

Capital Expenditure Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small local capital-expenditure planning helper that returns advisory JSON and does not show hidden access, persistence, external calls, or financial transaction capability.

Installers should treat this as informational financial planning support, not professional advice. It appears safe from a security perspective, but users should avoid relying on its generic recommendations for high-stakes investment or budgeting decisions without review by qualified professionals.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest sets "language": "en", which is a natural-language locale constraint. There is no indication elsewhere in the file that users can choose another language or that the English-only restriction is justified by a region-specific requirement.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The module-level documentation states there is no real code execution or financial transactions. However, the file defines executable logic, accepts input from argv/stdin, parses it, and emits a generated JSON response. While it does not perform dangerous side effects, the wording actively contradicts the fact that code is in fact executed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.