Ceo Protocol Skill

WarnAudited by ClawScan on May 10, 2026.

Overview

This DeFi skill is coherent, but it can use a wallet private key to submit on-chain transactions while its metadata does not declare that credential or the needed setup.

Only install this if you understand the DeFi protocol and are comfortable giving an agent a dedicated wallet key. Use a new low-balance wallet, review every proposed action and proposal URI, run dry-runs first, and do not let the agent sign transactions automatically.

Findings (3)

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.

Concern

ASI03: Identity and Privilege Abuse

What this means

If AGENT_PRIVATE_KEY is present, the agent can sign blockchain transactions from that wallet, spending gas and exercising whatever authority that wallet has.

Why it was flagged

The script requires a raw wallet private key and turns it into a signing account. The registry metadata declares no required env vars or primary credential, so this high-impact authority is under-declared.

Skill content

const account = privateKeyToAccount(requiredEnv("AGENT_PRIVATE_KEY"));

Recommendation

Use only a dedicated low-balance agent wallet, never a main wallet, and require explicit user approval before any signed transaction.

Concern

ASI02: Tool Misuse and Exploitation

What this means

An agent using this skill could submit on-chain governance proposals without an additional built-in approval prompt, which may spend gas and affect protocol governance.

Why it was flagged

The script supports a dry-run, but the default path broadcasts a CEOVault transaction. This is expected for a DeFi governance skill, but it is high-impact and the artifacts do not show an explicit confirmation gate.

Skill content

if (dryRun) { ... return; }

  const hash = await walletClient.writeContract({
    address: CEO_VAULT,
    abi: CEO_VAULT_ABI,
    functionName: "registerProposal",

Recommendation

Run with --dry-run first, inspect the proposal actions and URI, and require explicit confirmation before broadcasting any transaction.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing this skill as documented may add extra skills and npm packages that were not part of the main skill’s install metadata.

Why it was flagged

The skill asks users to install companion skills and npm dependencies even though the registry lists no install spec. This is disclosed and related to the protocol workflow, but it expands the trusted code base.

Skill content

Install these companion skills from ClawHub... clawhub install fabriziogianni7/8004-skill-monad ... clawhub install fabriziogianni7/pond3r-skill ... run `cd scripts && npm install` once

Recommendation

Review the companion skills and the npm lockfile before installing, and install in a controlled environment.