Security audit

vestafolio-micro-entreprise

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed tax-simulator helper that sends only user-approved inputs to Vestafolio and does not include executable code or persistence.

Before installing, understand that the skill is designed to send your simulator inputs, such as revenue, expenses, tax rate, fiscal parts, and RFR N-2, to Vestafolio after your approval. Do not approve the API call if you do not want those financial/tax inputs sent externally; use the manual simulator link instead.

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

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 (1)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The test instructions explicitly require real HTTP calls against a target host, but they do not require any user-facing notice, consent, or safeguards around network transmission. In an agent skill context, this can cause unintended external requests and disclosure of user-provided financial or tax inputs to a remote API during evaluation or use.

Static analysis

No suspicious patterns detected.