Back to skill

Security audit

vestafolio-interets-composes

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed compound-interest calculator that sends only user-approved simulation inputs to Vestafolio's API and shows no hidden persistence or privilege behavior.

Before installing, be aware that calculations rely on Vestafolio's external API. Only approve API calls when you are comfortable sending the listed simulator inputs, and avoid including personal identifiers, account details, credentials, files, or broader conversation history.

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 99)May include surrounding context.

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

bash
curl --fail-with-body --silent --show-error --max-time 30 -X POST https://www.vestafolio.com/api/tools/v1/interets-composes \
  -H 'Content-Type: application/json' \
  -d '{
    "initialAmount": 10000,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The file contains a natural-language policy constraint: "Reply in French whenever the user speaks or writes in French." This enforces a locale/language behavior automatically rather than presenting it as a user-selectable preference, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.