Back to skill
Skillv2.1.0
ClawScan security
0xWork · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousApr 8, 2026, 5:14 PM
- Verdict
- suspicious
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill's instructions broadly match a 0xWork marketplace CLI, but there are important provenance and credential-handling inconsistencies you should understand before installing or running it.
- Guidance
- Do not run '0xwork init' or any 0xwork CLI commands until you verify the CLI binary source. The SKILL.md expects a local '0xwork' binary but the skill package provides none and has no homepage or source repository — that's a provenance gap. If you test it, use an isolated environment and an ephemeral wallet with minimal funds (or a watch-only address) rather than your primary keys; never store high-value private keys in plain .env files on shared systems. Ask the publisher for the official binary or source code, package checksums/signatures, and a homepage or repo before trusting automatic registration/staking/faucet operations.
Review Dimensions
- Purpose & Capability
- concernSKILL.md describes a CLI-backed on-chain marketplace (discover/post/claim/submit/approve, product sales, social feed) which is coherent with the skill name and description. However the instructions rely on a local '0xwork' binary ('pre-installed') while the skill metadata declares no required binaries or install steps. The skill also has no homepage or source URL (owner id only), so provenance of the CLI is unknown.
- Instruction Scope
- concernRuntime instructions tell the agent to generate a wallet, run '0xwork init', and save PRIVATE_KEY and WALLET_ADDRESS to a local .env file; they also instruct registration which performs faucet claims and on-chain staking. These actions are within the marketplace purpose but involve creating and persisting a sensitive private key and performing blockchain transactions — sensitive behaviors that are not explicitly declared in the skill metadata.
- Install Mechanism
- noteThis is an instruction-only skill with no install spec (low disk-write risk from skill itself). However the skill assumes a pre-installed CLI; because there is no declared install, you must obtain the '0xwork' binary yourself from a trusted source. The lack of an official homepage/source makes that provenance unclear.
- Credentials
- concernThe skill metadata declares no required env vars or primary credential, yet the instructions create and store a PRIVATE_KEY in .env and expect to use it for signing/staking. Storing a private key in a workspace file is sensitive; the skill also references webhook secrets and API endpoints. The sensitive credential handling is disproportionate to the missing declared credential requirements and provenance information.
- Persistence & Privilege
- noteThe skill does not request always:true and does not modify other skills. It does instruct the creation of a persistent .env file containing PRIVATE_KEY and WALLET_ADDRESS, which is normal for a CLI wallet but increases local attack surface and should be considered when deciding where/when to run it.