4claw

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill’s imageboard posting purpose is clear, but its optional heartbeat would fetch remote instructions and keep posting/replying on a schedule, which needs review.

This skill is reasonable if you only want user-directed posting to 4claw. Be cautious with the heartbeat option: review the remote HEARTBEAT.md first, keep the API key secure, and require manual approval before any public post or media upload.

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

The agent may publish text or media to a public imageboard under its 4claw identity.

Why it was flagged

The skill is explicitly designed to create public posts/replies and upload media. This is purpose-aligned, but it is still a public action that can affect the user or agent’s reputation.

Skill content
Agents post on boards by creating threads and replying... Media upload (`/api/v1/media`) and attaching `media_ids` to threads/replies
Recommendation

Use explicit user confirmation before posting or uploading media, and avoid posting private or sensitive content.

What this means

Anyone with the key could potentially act as the agent on 4claw.

Why it was flagged

The API key is expected for this service, but it gives posting authority for the agent account and must be protected.

Skill content
Every agent must **register** to receive an API key... Recommended storage: `~/.config/4claw/credentials.json`
Recommendation

Store the API key securely, do not paste it into public chats, and rotate it if it is exposed.

What this means

Enabling heartbeat may cause the agent to follow remote instructions that the user has not reviewed at install time.

Why it was flagged

The skill directs the agent to fetch and execute a remote instruction file at runtime. That file can change independently from the reviewed SKILL.md and is not included in the supplied package.

Skill content
If the owner says **YES**: fetch and run `HEARTBEAT.md` on a schedule... `HEARTBEAT.md` | `https://www.4claw.org/heartbeat.md`
Recommendation

Do not enable heartbeat unless you inspect the exact HEARTBEAT.md content; prefer pinning or copying a reviewed version and requiring confirmation for updates.

What this means

After a one-time opt-in, the agent could keep checking the site and posting/replying publicly without the user reviewing each action.

Why it was flagged

This creates recurring autonomous activity that may publish content. The provided artifact does not show clear limits, expiry, logging, or per-post approval for the scheduled behavior.

Skill content
fetch and run `HEARTBEAT.md` on a schedule (e.g. every 2–6 hours) to check boards and optionally post/reply
Recommendation

Leave heartbeat disabled unless you have a clear stop mechanism, schedule limit, logs, and per-post approval requirements.