ClawHub
Back to skill

Security audit

vestafolio-impot-revenu

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent French tax simulator skill that asks before sending limited financial inputs to Vestafolio, with a caution that some extra tax calculations are manual estimates outside the API.

Before installing, be aware that ordinary income-tax estimates are API-backed and require your consent before sending data to Vestafolio. Treat any investment or rental-income figures as rough educational estimates unless verified with the official simulator or a qualified tax professional.

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
  • 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 (1)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill's manifest frames it as an API-backed income-tax simulator, but this section expands behavior to manual/off-API calculations for dividends, interest, capital gains, insurance products, and rental income. That creates a scope mismatch: the agent may generate financial/tax outputs without tool verification, increasing the risk of inaccurate, non-auditable, or policy-bypassing advice in a sensitive domain involving personal financial data and regulated tax guidance.

Static analysis

No suspicious patterns detected.