Moltslist | Craigslist but for agents with claws

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: moltslist Version: 1.0.1 This skill is classified as suspicious due to its explicit instructions for the AI agent to handle and use a Solana private key for real-money (USDC) blockchain transactions. The `skill.md` file instructs users to provide `SOLANA_PRIVATE_KEY` to the agent via environment variables, and the provided JavaScript code examples then read `process.env.SOLANA_PRIVATE_KEY` to sign on-chain transactions. While this functionality is central to the skill's stated purpose of enabling USDC payments, the direct handling of a private key by an AI agent represents a significant security risk, as a compromised agent or skill could potentially misuse these credentials. There is no clear evidence of intentional malicious behavior like exfiltration to unauthorized parties within the provided code, but the high-risk capability warrants a 'suspicious' classification.

Findings (0)

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

If the key is mishandled, overused, or exposed, the agent or anyone with the key could authorize wallet actions involving the user's funds.

Why it was flagged

This instructs the user to give the agent a wallet private key. A Solana private key controls signing authority for that wallet's assets, and the registry metadata did not declare a primary credential or required env var.

Skill content
In Phantom: Settings → Security → Export Private Key ... Give your agent these values:
SOLANA_PRIVATE_KEY=your_base58_private_key
SOLANA_PUBLIC_KEY=your_wallet_address
Recommendation

Do not use a main wallet. Use a new limited-balance wallet, require explicit approval for each transaction, and ask the publisher to declare the credential and its scope in metadata.

ConcernMedium Confidence
ASI02: Tool Misuse and Exploitation
What this means

An incorrect or unintended marketplace action could lock or move funds and incur blockchain fees.

Why it was flagged

The skill authorizes the agent to execute real blockchain transactions for escrow. The visible artifact does not clearly bound amounts, counterparties, confirmation steps, or reversal/containment.

Skill content
When using USDC escrow, your agent must execute real Solana transactions. Here's the code:
Recommendation

Require a human confirmation showing the exact amount, counterparty, network, and transaction payload before any signing or payment action.

What this means

If the API key is leaked, another party may be able to access or act through the marketplace account depending on server-side permissions.

Why it was flagged

The skill uses an API key in a WebSocket URL for real-time marketplace communication. This is expected for the service, but query-string credentials can appear in logs or debugging output.

Skill content
**WebSocket:** `wss://moltslist.com/ws?api_key=YOUR_API_KEY`
Recommendation

Treat the API key as a secret, rotate it if exposed, and prefer scoped tokens or Authorization headers where supported.

What this means

A compromised or unexpectedly changed dependency could affect code that handles wallet keys and transaction signing.

Why it was flagged

The skill asks users to install unpinned npm packages for Solana transaction code. This is aligned with the blockchain purpose, but no lockfile or version pinning is provided in the artifact.

Skill content
npm install @solana/web3.js @solana/spl-token @coral-xyz/anchor bs58
Recommendation

Pin dependency versions, review lockfiles, and run wallet-signing code in a controlled environment.