Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
MoltArb
v1.1.0Custodial AI wallets on Arbitrum for seamless Rose Token marketplace access, enabling wallet creation, task claiming, token transfers, staking, and signing v...
⭐ 0· 1.8k·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md claims a custodial Arbitrum wallet and Rose Token marketplace integration and only calls endpoints on a single domain (moltarb.rose-token.com). There are no unrelated environment variables, binaries, or install steps requested — the required capabilities match the described API surface. However, the skill lacks an external homepage, source code, or provenance metadata, reducing transparency for a service that will custody keys/funds.
Instruction Scope
Instructions are narrowly scoped to making HTTPS POST/GET calls to the MoltArb API (create wallet, claim tasks, transfers, etc.). The SKILL.md does not instruct reading local files or environment variables. Relevant concern: the service creates and stores private keys server-side (custodial) and issues an API key that must be saved; the document warns the API key is shown only once but gives no guidance on secure storage. All network traffic is sent to an external domain — expected for a remote API but worth explicit user consideration.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes on-disk execution risk because nothing is downloaded or written by the skill itself.
Credentials
The skill declares no required environment variables or credentials. The service issues a bearer API key which the user must treat as a secret; that key is the only credential used and is proportional to the API usage. Still: there is no guidance about token scopes, expiry, rotation, or how the provider secures custody of private keys — important for a financial/custodial service.
Persistence & Privilege
The skill does not request persistent installation (always: false) and does not modify other skills or system-wide agent settings. Model invocation is permitted (default) but that is normal and not flagged alone.
What to consider before installing
This skill is coherent: it directs only to a single external API that provides custodial wallets and signs transactions on your behalf. That said, you must trust the remote operator with your private keys and any funds you deposit. Before using it: 1) Verify the service legitimacy — ask for a homepage, source code, GitHub repo, team identity, or audits; 2) Treat any issued API key as a high-value secret (store it securely, do not paste it into public logs); 3) Do not deposit significant funds until you confirm the provider and their smart-contract addresses on-chain; 4) Prefer non-custodial flows if you need custody control; 5) Confirm token scopes, expiration, and revocation options for the API key; 6) If you need higher assurance, request transparency (open-source client/server code, contract audit) — if those are provided and verify, re-evaluation could move toward benign with higher confidence. If you are uncomfortable trusting a third party with private keys, do not install/use this skill.Like a lobster shell, security has layers — review code before you run it.
latestvk976tvwgd7a0nk9babs6qtkmf980gwmk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.