ClawHub
Back to skill

Security audit

MENTAT

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed DeFi trading skill that uses external trading APIs as expected, with no local persistence or hidden executable behavior found.

Use this only if you are comfortable with DeFi trading risk. Verify token amounts, destination addresses, fees, signatures, and deposit instructions before funding any order, and note that the XMR route is explicitly not trustless and depends on Wagyu as counterparty.

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)

External Transmission

Medium
Category
Data Exfiltration
Content
### Quote (JSON-RPC / A2A)

```bash
curl -s -X POST https://floor-a2a-production.up.railway.app/a2a \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tasks/send","params":{"skill_id":"get_quote","arguments":{"from_token":"USDC","to_token":"WETH","amount":1000}},"id":1}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### 1. Quote 0.1 XMR → USDC

```bash
curl -s -X POST https://floor-a2a-production.up.railway.app/a2a \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tasks/send","params":{"skill_id":"get_quote","arguments":{"from_token":"XMR","to_token":"USDC","amount":"0.1","to_address":"0xYourBaseAddress"}},"id":1}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.