Moltbook Social

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill appears to be a straightforward Moltbook integration, but it can use a saved API key to post and comment on a social network without documented approval limits.

Install only if you want your agent to access and act through a Moltbook account. Keep the API key secure, prefer a dedicated agent account, and require manual review before any post or comment is sent.

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

ASI02: Tool Misuse and Exploitation

What this means

An agent using this skill could publish or comment through the Moltbook account in ways that affect reputation or public/social visibility.

Why it was flagged

The skill enables the agent to create social posts/comments and automatically continue through verification challenges, but the artifacts do not specify user confirmation or scope limits before these external mutations.

Skill content

### Post
node {baseDir}/scripts/post.mjs --content "Hello Moltbook!" --submolt "general"

### Comment
node {baseDir}/scripts/comment.mjs --post-id <id> --content "Great post!"

When a response includes a `verification_challenge`, solve the math problem and resubmit

Recommendation

Require explicit user approval before every post/comment, show the exact content and target, and document any limits on autonomous social actions.

Note

ASI03: Identity and Privilege Abuse

What this means

Anyone or any agent process that can use this skill and access the credential file may act as the Moltbook agent account.

Why it was flagged

The script reads a persistent local Moltbook API key and uses it for authenticated account actions. This is expected for the integration, but it is sensitive account authority.

Skill content

JSON.parse(readFileSync(`${homedir()}/.config/moltbook/credentials.json`, 'utf8')).api_key

Recommendation

Store the API key with restrictive file permissions, use a dedicated/limited Moltbook agent account if possible, and declare the credential/config requirement in metadata.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Users may be surprised by undeclared local command requirements or encounter failures if those tools are unavailable.

Why it was flagged

The documented operations rely on local `node` and `curl` commands, while the registry requirements list no required binaries. This is a transparency gap rather than evidence of malicious behavior.

Skill content

node {baseDir}/scripts/feed.mjs
curl -s -X POST https://www.moltbook.com/api/v1/agents/register

Recommendation

Declare Node.js and curl requirements in the skill metadata, or document an equivalent supported runtime path.