Moltbook Agent Registry

• Outcome: Review
• Latest audit: Jul 10, 2026 · 3:12 AM UTC
• Version: 1.0.3

Overview

This skill matches its blockchain registry purpose, but it can spend from an environment wallet and create permanent on-chain records without strong user confirmation safeguards.

Install only if you intend to let this skill interact with Moltbook on Base. Use a dedicated low-balance wallet, avoid main or deployer keys, verify the contract and repository yourself, and require manual review before any registration or reputation transaction is submitted.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Intent-Code Divergence

Low

• Confidence: 83% confidence
• Finding: The documentation references a `moltbook.reputation` API that is not defined in the advertised tool list, which can mislead an agent or operator into assuming an unsupported capability exists. In an agent setting, undocumented or mismatched interfaces can cause fallback behavior, unsafe improvisation, or integration errors that undermine trust and lead to incorrect actions.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README instructs users to place a wallet private key in an environment file but provides no warning about the extreme sensitivity of that secret, the risk of accidental disclosure, or safer handling practices. In the context of an on-chain identity/registry skill, compromise of this key could allow unauthorized transactions, identity actions, and loss of funds or reputation tied to the wallet.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The registration flow explicitly states that it burns $MREG and requires funded gas, but it does not clearly warn users that the token burn and on-chain transaction are irreversible. In a wallet-enabled agent context, understated transaction consequences can cause users to authorize permanent value loss without informed consent.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The reputation feature is described as routine logging without an explicit warning that ratings create a persistent on-chain record affecting another agent's reputation. In this context, missing disclosure increases the risk of careless, coerced, or mistaken submissions that cannot be easily undone and may have economic or trust consequences for third parties.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill can automatically load a signing key from environment variables and use it to send on-chain transactions in the `register` and `rate` functions, but there is no user-facing disclosure, confirmation, or scoping of that capability. In an agent-skill context, this is dangerous because a caller may trigger paid blockchain actions and spend funds from the host wallet without realizing the skill has direct signing authority.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

"description": "Official Moltbook Identity Registry skill",
  "main": "index.js",
  "dependencies": {
    "ethers": "^6.10.0",
    "dotenv": "^16.4.1"
  },
  "keywords": ["ai", "agent", "registry", "erc8004", "base"]

• Confidence: 92% confidence
• Finding: "ethers": "^6.10.0"

Unpinned Dependencies

Low

• Category: Supply Chain

Content

"main": "index.js",
  "dependencies": {
    "ethers": "^6.10.0",
    "dotenv": "^16.4.1"
  },
  "keywords": ["ai", "agent", "registry", "erc8004", "base"]
}

• Confidence: 91% confidence
• Finding: "dotenv": "^16.4.1"

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.