Kite Agent Smart Wallet Permissionless Protocol
v1.0.0Create and manage modular, permissioned smart wallets for AI agents with session keys and spending limits on the Kite AI network.
⭐ 0· 293·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (smart-wallet protocol for AI agents) aligns with the provided SKILL.md, README, and skill.json: all describe contract addresses, testnet/mainnet RPCs, and example ethers.js usage. There are no unrelated credentials, binaries, or install steps requested.
Instruction Scope
SKILL.md contains usage examples (ethers.js snippets) and protocol documentation only. It does not instruct the agent to read local files, environment variables, or system state, nor to send data to unexpected external endpoints beyond the stated RPC/explorer URLs.
Install Mechanism
No install spec or code files are present; this is an instruction-only skill. No downloads or archive extraction occur, which minimizes filesystem risk.
Credentials
The skill declares no required environment variables or credentials. Practically, performing the shown actions (creating wallets, sending transactions) requires a signer/private key and a provider RPC — but the skill does not request or attempt to access such secrets itself. This is proportionate, but operators must supply signing credentials externally.
Persistence & Privilege
Skill is not always-enabled and does not request persistent system privileges or modify other skills. It is user-invocable and allows model invocation (platform default), which is expected for functional skills.
Assessment
This skill is documentation/instruction for a smart-wallet protocol — it itself doesn't require or hold your private keys. Before using it: (1) Verify the contract addresses and source on the Kite block explorer; (2) test on the Kite testnet (RPC/faucet) before mainnet; (3) never paste private keys or long-term signing secrets into chat or into an agent without explicit safeguards; (4) ensure any agent you allow to sign transactions is limited via session keys / spending limits as described; (5) if you need higher assurance, review the smart contract source code (on-chain or repo) to confirm the modules behave as documented.Like a lobster shell, security has layers — review code before you run it.
latestvk9780yjhn6by1mfz8vdmxk16zx81vw2f
License
MIT-0
Free to use, modify, and redistribute. No attribution required.