Rei-Clawd
Analysis
Rei-Clawd transparently configures a third-party Rei model provider, but running it will store a Rei API key and change/restart Clawdbot configuration.
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
jq --argjson rei "$REI_PROVIDER" '.models.providers.rei = $rei' "$CONFIG_FILE" > "${CONFIG_FILE}.tmp" && mv "${CONFIG_FILE}.tmp" "$CONFIG_FILE"The setup script directly edits the Clawdbot model-provider configuration; nearby instructions also restart the gateway. This is expected for the stated setup purpose, but it changes agent routing behavior.
Source: unknown Homepage: none
The registry metadata does not provide a source repository or homepage. The included script contents are visible and simple, so this is a provenance note rather than a concrete unsafe behavior.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
read -p "Enter your Rei API key: " API_KEY ... "apiKey": "$API_KEY"
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.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Rei provides Qwen3 Coder via an OpenAI-compatible endpoint at `coder.reilabs.org`.
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.