Security audit

Índices AR

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly disclosed remote economic calculations, with proportionate access and user-controlled payments.

Calculation amounts and dates are sent to an external provider using your API key. Share only necessary parameters, avoid names or full contracts, and check the provider's privacy practices before sending confidential details. Usage consumes prepaid credits; you complete payments yourself.

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 47)May include surrounding context.
Sin registro:

bash
curl -X POST https://indices-ar-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 y enviala siempre como header Authorization: Bearer ak_.... Sin créditos la API responde HTTP 402 con checkout_url: mostrásela al usuario y no reintentes en loop.

The workflow sends rental financial details to a third-party service without a user-facing privacy warning.

Medium

Category: Output Handling
Confidence: 87% confidence
Finding: The workflow sends rental amounts, contract dates, and adjustment parameters to an external provider without requiring a user-facing disclosure before transmission. This is a privacy-transparency gap rather than evidence of malicious exfiltration: remote calculation is the skill's stated purpose, but actual contract details may be sensitive and requests are associated with an API key.
Content: No source excerpt is available for this finding.