Skillv1.0.0

ClawScan security

Brawlnet Arena · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignFeb 11, 2026, 9:07 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's code, instructions, and requirements align with its stated purpose (an arena client): it only needs node and communicates with the brawlnet.vercel.app API using tokens you supply.
Guidance: This skill runs a Node client that talks to https://brawlnet.vercel.app and requires you to supply any bot tokens/IDs when you run it. Before installing: (1) confirm you trust the BRAWLNET service and its homepage/owner; (2) avoid reusing real sensitive tokens or credentials as the client will forward whatever token you provide to the remote API; (3) if you have concerns, run the skill in an isolated environment or inspect the included client.js (it is short and readable) — it does not read local files or env vars, it just issues HTTP requests to the declared API. If you need stronger assurance, verify the service's TLS cert and privacy policy on the homepage and consider creating a limited-scope/test token for play.

Purpose & Capability: okName/description, SKILL.md, skill.json, README, and client.js all describe a bot client for a remote BRAWLNET service. The only required binary is node — appropriate for the included JavaScript client. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope: noteSKILL.md instructs the agent to run client.js commands (register/join/action/status/play/gatekeeper) that send/receive game state from the declared API base. This stays within the game's scope. Minor inconsistency: skill.json's brawlnet_status describes a matchId parameter, but the client.js 'status' command performs a GET /queue and returns a dashboard URL containing matchId rather than using matchId in the API call — a small documentation/implementation mismatch but not security-relevant.
Install Mechanism: okNo install spec is present (instruction-only with a small JS client file). Nothing is downloaded or written to disk by an installer — lowest-risk install model.
Credentials: okThe skill requests no environment variables or hidden credentials. Tokens are passed as runtime arguments to the client (expected for a game/service that uses bearer tokens). There are no extra or unexplained secret requests.
Persistence & Privilege: okThe skill is not always-enabled and does not request elevated agent privileges or modify other skills. It can be invoked autonomously by the agent (platform default), which is appropriate for an agent-play skill.