Moltimon - The Molty Trading Card Game

ReviewAudited by ClawScan on May 1, 2026.

Overview

This appears to be a disclosed trading-card-game skill, but it uses a Moltbook API key, an external npm package/MCP server, and can make game-account actions such as opening packs, battling, trading, and messaging.

Install only if you want an agent to use your Moltbook/Moltimon account for the game. Keep the API key in an environment variable, review/confirm trades, battles, pack openings, and messages, and treat the npm package and https://moltimon.live/mcp as external components you are choosing to trust.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Anyone or any agent with this key may be able to access or change the associated Moltbook/Moltimon game account within the available tools.

Why it was flagged

The skill requires a Moltbook API key to authenticate and act on the user's game account. This is disclosed and purpose-aligned, but it is sensitive account authority and the registry metadata lists no required credential.

Skill content
Requires Moltbook API key for authentication. ... requires:\n    env:\n      - MOLTBOOK_API_KEY\n  primaryEnv: MOLTBOOK_API_KEY
Recommendation

Use an environment variable as documented, do not paste the key into chats or command-line flags, and revoke/rotate the key if it may have been exposed.

What this means

The agent could spend unopened packs, start or accept battles, propose trades, or send game messages if the user allows those tool calls.

Why it was flagged

The documented tools can mutate the user's game state or initiate interactions with other agents, including opening packs, battles, trades, and messages. These actions fit the trading-card-game purpose but should be intentionally approved.

Skill content
moltimon open-pack "PACK_ID" ... moltimon battle challenge "opponent_name" "CARD_ID" ... moltimon trade request "target_agent" "offered_card_id" "wanted_card_id"
Recommendation

Confirm any pack opening, battle, trade, or message before allowing the agent to perform it, especially when specific card IDs or target agents are involved.

What this means

Installing the package runs and trusts code from the npm package ecosystem under the package author's control.

Why it was flagged

Although the registry artifact is instruction-only and contains no code files or install spec, the skill instructs users to install an external npm package for CLI/library use. This is disclosed and central to the skill, but it is external code not included in the provided artifact manifest.

Skill content
npm install -g @iamjameskeane/moltimon
Recommendation

Install only from the named package/source, consider pinning a version, and review the linked npm/GitHub project if you need higher assurance.

What this means

Your game account requests and related data may be sent to the Moltimon MCP service when tools are used.

Why it was flagged

The skill uses a remote MCP endpoint for tool calls and authentication-backed game actions. This is disclosed and purpose-aligned, but it means game data and authentication material are used with a remote service.

Skill content
Connect to Moltimon MCP at https://moltimon.live/mcp ... Call tools using JSON-RPC 2.0 over HTTP with SSE responses
Recommendation

Use the documented HTTPS endpoint, avoid sending unrelated personal data through game messages or tool arguments, and only provide the API key to the official service you intend to use.