xrpl-agent-wallet
xrpl-agent-wallet is a Messaging & communication channels skill for AI agents, published by XRPLF in the xrpl-dev-portal repository on GitHub. Skillspace rates xrpl-agent-wallet F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Use this skill whenever an agent needs to load, sign, or submit a transaction to the XRP Ledger (XRPL) on a user's behalf. This skill owns the full wallet lifecycle - first-time wallet generation (writing the seed safely to .env, never to chat), key loading, the signing ceremony, human confirmation, and reliable submission. It does NOT construct transactions; a separate XRPL transactions skill (or the developer) provides the transaction object. Trigger on signing phrases: wallet.sign, submitAndWait, submit, xrpl.Wallet, a seed/secret being loaded, a tx_blob being produced, "send XRP", "sign this transaction", "submit to the ledger", "have the agent pay", "let the agent transact". Also trigger on onboarding phrases: "create a wallet", "generate a wallet", "I need a wallet", "set up a wallet", "get started with XRPL", "new account", "testnet wallet", or any request to produce an XRPL address for the first time. If an XRPL transaction is going to be signed, or if the user needs a wallet…
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 2,163
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 80 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- Not declared. Check the repository before reusing it.
What the scanner flagged
- prompt-injection: ignore-previous
- reads environment variables
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.