Back to skill

Security audit

vestafolio-choisir-regime

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed French business-structure simulator helper that asks consent before sending a limited profile to Vestafolio's API.

Before installing, be aware that using the simulator means sending your activity type, projected turnover, and related business preferences to Vestafolio after you approve the call. Do not include names, addresses, credentials, or sensitive documents; use the manual simulator link instead if you do not want network transmission.

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
  • 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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The skill instructs the agent to transmit user-supplied business profile data to an external domain, which is a genuine data egress path. Although the skill includes meaningful safeguards—data minimization, destination disclosure, and explicit user agreement—the external POST still creates privacy and compliance risk if consent is skipped, misunderstood, or overly broad in practice.

Content

Scanner excerpt · SKILL.md (reported line 148)May include surrounding context.

Then POST the user's profile (amounts in euros):

bash
curl --fail-with-body --silent --show-error --max-time 30 -X POST https://www.vestafolio.com/api/tools/v1/choisir-regime \
  -H 'Content-Type: application/json' \
  -d '{
    "activityCategory": "services_bnc",

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill includes a natural-language policy constraint: "Reply in French whenever the user speaks or writes in French." This imposes a locale/language behavior and does not explicitly mention that the user may choose another language instead, which can conflict with language-choice policies unless clearly justified or opt-in based.

Content

No source excerpt is available for this finding.