xrpl-agent-wallet
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies and mitigates indirect prompt injection risks by treating transaction memo fields as untrusted input (Ingestion point). It enforces a strict signing ceremony with rigid preview formatting (Boundary marker) before exercising its signing capabilities (Capability inventory), and provides instructions to ignore instructions found in external data (Sanitization).\n- [CREDENTIALS_UNSAFE]: The skill follows secure credential management practices by generating XRPL seeds and writing them directly to a local .env file. It explicitly forbids the agent from ever displaying, logging, or echoing these secrets in the chat transcript or any external logs.\n- [EXTERNAL_DOWNLOADS]: The skill references official XRPL tools such as the Testnet faucet and well-known public ledger endpoints. These are trusted infrastructure components and are necessary for the skill's documented purpose.\n- [COMMAND_EXECUTION]: Code snippets within the skill perform legitimate file system updates to configuration files (.env and .gitignore) and interact with the ledger through the standard xrpl Node.js library.
Audit Metadata