Rei-Clawd

PassAudited by ClawScan on May 1, 2026.

Overview

Rei-Clawd transparently configures a third-party Rei model provider, but running it will store a Rei API key and change/restart Clawdbot configuration.

Install/run this only if you intend to use Rei as a Clawdbot model provider. Protect the Rei API key, review ~/.clawdbot/clawdbot.json after setup, keep the backup for rollback, and remember that using the Rei model sends relevant prompts/code context to coder.reilabs.org.

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

Running the setup can alter which model provider Clawdbot uses and restart the gateway.

Why it was flagged

The setup script directly edits the Clawdbot model-provider configuration; nearby instructions also restart the gateway. This is expected for the stated setup purpose, but it changes agent routing behavior.

Skill content
jq --argjson rei "$REI_PROVIDER" '.models.providers.rei = $rei' "$CONFIG_FILE" > "${CONFIG_FILE}.tmp" && mv "${CONFIG_FILE}.tmp" "$CONFIG_FILE"
Recommendation

Run it only when you intend to add Rei, review the resulting config, and keep the backup/revert path available.

What this means

Anyone with access to the Clawdbot config or a transcript where the key was pasted could potentially see the Rei API key.

Why it was flagged

The script collects a Rei API key and writes it into the provider configuration. This is necessary for the integration, but it is still sensitive credential handling.

Skill content
read -p "Enter your Rei API key: " API_KEY ... "apiKey": "$API_KEY"
Recommendation

Use a dedicated, revocable Rei API key, avoid pasting it into shared chats, and protect ~/.clawdbot/clawdbot.json.

What this means

Users have less publisher/provenance context for a skill that changes local Clawdbot configuration.

Why it was flagged

The registry metadata does not provide a source repository or homepage. The included script contents are visible and simple, so this is a provenance note rather than a concrete unsafe behavior.

Skill content
Source: unknown
Homepage: none
Recommendation

Verify that you trust the registry owner and the coder.reilabs.org service before running the setup.

What this means

When Rei is selected, your model traffic may be processed by the external Rei endpoint.

Why it was flagged

The skill configures an external model endpoint. That is the core purpose, but future prompts, code, and context sent to the Rei model will leave the local Clawdbot environment.

Skill content
Rei provides Qwen3 Coder via an OpenAI-compatible endpoint at `coder.reilabs.org`.
Recommendation

Use Rei only for data you are comfortable sending to that provider, and switch back or revert if you do not want that routing.