Back to skill

Security audit

Radar CNPJ

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Radar CNPJ integration that uses external API calls for its stated company-checking purpose and includes explicit user-approval rules for paid or personal-data actions.

Before installing, be aware that queries go to radar-cnpj.com and that paid lookups, credit tokens, partner names, phone numbers, and email reveals require careful user approval and legitimate use. The skill itself tells the agent not to spend balance, reveal personal data, or log tokens without user control.

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
  • 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 (1)

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 73)May include surrounding context.

bash
# Company record (free)
curl -s https://radar-cnpj.com/api/cnpj/33000167000101

# Companies by name and state (free)
curl -s 'https://radar-cnpj.com/api/busca?q=padaria&uf=DF'

Static analysis

No suspicious patterns detected.