ClawHub
Back to skill

Security audit

XRPL x402 Handoff

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only XRPL payment handoff skill with disclosed payment safeguards and no executable install behavior.

Before using this skill for mainnet payments, verify the facilitator, seller, amount, network, and recipient independently, set low spend ceilings, and remember XRPL payments may be irreversible. Keep wallet seeds out of chat and prefer testnet for demos.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README explicitly instructs the user to pay an XRPL x402 challenge over the network, but the only safety boundary mentioned is not to share a seed in chat. That leaves out key safeguards such as verifying the recipient, validating the challenge source, enforcing spend limits, and warning about irreversible transfers, which could enable social engineering or unauthorized payment execution.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The instruction 'Refuse mainnet until human says SÍ' hard-codes a Spanish approval phrase as the required trigger for a critical action. This is a language/locale policy issue because it imposes a specific language choice without offering an alternative or documenting a justified locale constraint.

External Transmission

Medium
Category
Data Exfiltration
Content
## References (read, do not hardcode secrets)

- Protocol skill (example facilitator): https://api.xrplfi.com/skill.md
- Catalog: https://api.xrplfi.com/catalog
- OSS facilitator/SDK: https://github.com/tekvyy/x402-xrpl
- t54-style XRPL x402 facilitator docs: https://xrpl-x402.t54.ai/
Confidence
50% 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
## References (read, do not hardcode secrets)

- Protocol skill (example facilitator): https://api.xrplfi.com/skill.md
- Catalog: https://api.xrplfi.com/catalog
- OSS facilitator/SDK: https://github.com/tekvyy/x402-xrpl
- t54-style XRPL x402 facilitator docs: https://xrpl-x402.t54.ai/
Confidence
50% 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.