Back to skill

Security audit

vestafolio-credit-immobilier

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed mortgage calculator integration that asks before sending only the needed loan inputs to Vestafolio’s API.

Before installing, understand that using the skill for a personalized calculation will send the mortgage amount, rate, duration, and insurance rate to Vestafolio after the agent asks for your approval. Do not provide unnecessary personal identifiers.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

Then POST the user's parameters (all amounts in euros, rates in percent):

bash
curl --fail-with-body --silent --show-error --max-time 30 -X POST https://www.vestafolio.com/api/tools/v1/credit-immobilier \
  -H 'Content-Type: application/json' \
  -d '{
    "principal": 250000,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The instruction says to reply in French whenever the user speaks or writes in French. Under the policy, language constraints should offer a user choice or clear opt-in unless the locale restriction is explicitly justified; this line imposes a language behavior without such opt-in.

Content

No source excerpt is available for this finding.