Sponge Wallet

Manage crypto wallets, transfers, swaps, and balances via the Sponge Wallet API.

This skill appears to do what it says (manage wallets via the Sponge Wallet API), but pay attention before installing: 1) SKILL.md tells agents to use an 'agent-first' registration flow that returns an API key immediately — that means an agent could perform transactions before a human explicitly claims the wallet. If you require human approval, prefer the standard device flow. 2) The skill instructs writing the API key to ~/.spongewallet/credentials.json (and exporting it). Confirm you are comfortable storing a live crypto API key on disk; consider using least-privilege keys or isolated accounts and rotate keys frequently. 3) The registry metadata did not declare the ~/.spongewallet config path even though the instructions use it — treat that as a minor inconsistency and verify how your agent runtime will handle the file. 4) Ensure the SPONGE_API_KEY you provide has only the permissions you expect; if possible test on testnet keys first. 5) Verify the skill's source/homepage before granting any live keys. If you need stricter guarantees (human-in-the-loop for any transfer or disabling agent-autonomy), require those controls before installing.

Type: OpenClaw Skill Name: wallet-skills Version: 0.1.2 This skill is classified as suspicious due to the exposure of several high-risk capabilities to the AI agent, which could be abused via prompt injection. Most notably, the `x402_fetch` endpoint allows the agent to make arbitrary HTTP requests to any URL and automatically pay for them using the agent's wallet, combining broad network access with financial expenditure. Additionally, the skill enables direct cryptocurrency transfers, swaps, bridges, Polymarket trading, and Amazon purchases, all of which are high-impact financial operations. While these features are intended, their broad scope and the agent's ability to execute shell commands (`curl`) based on `SKILL.md` instructions present a significant attack surface for unauthorized actions if the agent is compromised.