ClawHub
Back to skill

Security audit

Efectivo o Cuotas (ARGENTINA)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple payment-option calculator with a disclosed public inflation-data lookup, and no executable code, persistence, credential use, or destructive behavior.

Before installing, note that the skill is intended for Spanish-language answers and may query a public government data API if you do not provide the monthly opportunity rate. Provide the rate yourself or disable inflation projection if you want to avoid that lookup.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The entire skill specification mandates Spanish output such as 'La respuesta debe ser breve, numerica y directa' and all required output blocks are in Spanish, with no opt-in or alternative locale handling. This constitutes a language policy issue because the skill imposes a specific language on users without an explicit choice or documented regional limitation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly performs an external HTTP GET to a government API when a rate is missing, but the user-facing description does not disclose that network access may occur. This creates a transparency and privacy issue because user inputs or usage context may trigger outbound requests without informed consent, and the hidden dependency can surprise users or violate deployment expectations.

Static analysis

No suspicious patterns detected.