ClawHub
Back to skill

Security audit

ar-tools

Security checks for vulnerabilities and agentic risk

Overview

The skill provides the advertised remote validation service, with disclosed data sharing and credit charges that users should consider.

Use the service for lookups you intend to send externally, and check its privacy practices before submitting personal or banking identifiers. Protect the API key and expect prepaid-credit charges. The live service and publisher identity could not be independently verified during this review.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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 45)May include surrounding context.

Sin registro. Pedí una key de prueba:

bash
curl -X POST https://ar-tools-api-103907796853.us-east1.run.app/v1/keys -H 'content-type: application/json' -d '{"name":"mi-agente"}'

La respuesta trae key (empieza con ak_). Guardala: no se vuelve a mostrar. Enviala siempre como header Authorization: Bearer ak_....

The skill directs agents to send tax and banking identifiers to an external service without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill encourages automatic use when users mention identifiers and requires external tool calls for CUIT/CBU validation, without requiring informed authorization before transmitting potentially sensitive tax or banking data. Although external validation is the advertised functionality rather than concealed exfiltration, users may not expect identifiers supplied in conversation to leave the agent environment, and the skill provides no retention or privacy assurances.

Content

No source excerpt is available for this finding.