ClawHub
Back to skill

Security audit

dach-x402-compliance

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed wrapper for paid DACH compliance checks and does not install code, persist changes, or hide extra behavior.

Before installing, confirm you trust the provider and independently verify the Base network, USDC amount, pay-to address, and quote details before paying. Do not let an agent send blockchain payments automatically without explicit approval and a spending limit.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs users to send on-chain payment to a specific address and retry with a transaction hash, but it does not include an explicit warning to independently verify the recipient, amount, network, irreversibility of blockchain payments, or trustworthiness of the service before spending funds. In an agent setting, this omission increases the risk of unintended or automated value transfer to an external party based solely on documentation embedded in the skill.

Content

No source excerpt is available for this finding.

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 51)May include surrounding context.

Step 1: POST without payment → HTTP 402

bash
curl -s -X POST https://agent.kihustle.tech/services/impressum-check/jobs \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.de", "country": "DE"}'