ClawHub
Back to skill

Security audit

Luzia Crypto API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Luzia cryptocurrency market-data API guide, with expected third-party API calls and no hidden execution or persistence.

Install only if you intend to use Luzia as a third-party crypto market-data provider. Use a real Luzia API key through secure secret handling rather than hardcoding it, and avoid sending unnecessary sensitive information in symbols, requests, logs, or trading-bot code.

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 (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill is explicitly designed to connect to external endpoints at api.luzia.dev over HTTPS and WSS, which causes data to leave the local trust boundary. In context this is expected functionality, but it is still a real security-relevant behavior because prompts, requested market data parameters, and bearer credentials may be exposed to a third party if used without notice or proper secret handling.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
- **Base REST URL:** `https://api.luzia.dev`
- **WebSocket URL:** `wss://api.luzia.dev/v1/ws`
- **Swagger UI:** `https://api.luzia.dev/docs`
- **Docs:** `https://luzia.dev/docs`

---

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 525)May include surrounding context.

md
| Resource          | URL                                      |
|-------------------|------------------------------------------|
| Docs home         | https://luzia.dev/docs                   |
| Swagger UI        | https://api.luzia.dev/docs               |
| WebSocket docs    | https://luzia.dev/docs/websocket         |
| TypeScript SDK    | https://luzia.dev/docs/sdk               |
| Python SDK        | https://luzia.dev/docs/python-sdk        |

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs use of an authenticated third-party REST/WebSocket service but never warns that user-provided symbols, trading requests, and API credentials will be transmitted to luzia.dev. This creates a transparency and privacy issue: users or downstream agents may unknowingly send sensitive prompts, usage patterns, or secrets to an external service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.