Central de Deudores BCRA

• Outcome: Review
• Latest audit: May 27, 2026 at 10:02 PM UTC
• Version:
  1.0.0

Overview

The skill is instruction-only and purpose-aligned, but it enables lookup and display of sensitive credit/debt information by tax ID without clear consent or lawful-use guardrails.

Review before installing. Use this skill only for your own records or clearly authorized business/legal workflows, verify the CUIT/CUIL/CDI before querying, avoid sharing results unnecessarily, and prefer the official BCRA API over the optional third-party UI unless you intentionally want to use that site.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill is explicitly designed to retrieve and present a person's or company's credit and debt status using a national identifier, which is highly sensitive financial personal data. Without any warning, consent requirement, authorization check, or privacy handling guidance, the skill can facilitate unauthorized lookups, profiling, or disclosure of regulated financial information.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The OpenAPI spec exposes endpoints that retrieve sensitive financial and credit-status data using only a personal or corporate tax identifier (CUIT/CUIL/CDI), and the skill description explicitly encourages use for checking an individual's or company's debt situation. Even if the upstream BCRA API is public or authorized, the skill lacks any visible consent, authorization, purpose-limitation, or privacy-warning controls, creating a real risk of privacy abuse, unauthorized profiling, and disclosure of sensitive financial information.

VirusTotal

66/66 vendors flagged this skill as clean.