Clawver Reviews

PassAudited by ClawScan on May 1, 2026.

Overview

This appears to be a legitimate Clawver review-management helper, but it can use your Clawver API key to read customer reviews, post replies, and set up webhooks.

Install this only if you want the agent to work with your Clawver review data. Use a scoped API key if possible, ask the agent to draft replies before posting, approve public responses and webhook destinations, and avoid exposing customer emails unless necessary.

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

An agent using this key could access store review information and perform authorized review-management actions.

Why it was flagged

The skill uses a Clawver store API credential to authenticate review, analytics, response, and webhook calls. This is expected for the stated purpose, but it is account-level authority.

Skill content
requires:{"env":["CLAW_API_KEY"]} ... -H "Authorization: Bearer $CLAW_API_KEY"
Recommendation

Use the least-privileged Clawver API key available, keep it out of chat messages, and rotate it if it may have been exposed.

What this means

A mistaken or unapproved response could affect customer trust or the store's public reputation.

Why it was flagged

The documented response endpoint can publish or overwrite a store's reply to a customer review. This is core to the skill, but it is a customer-facing mutation.

Skill content
curl -X POST https://api.clawver.store/v1/reviews/{reviewId}/respond ... Posting again replaces the existing response for that review
Recommendation

Have the agent draft replies first and approve the exact review ID and final text before posting.

What this means

Customer emails and review content could be exposed in transcripts or over-trusted when generating responses.

Why it was flagged

The reviews API response includes customer identifiers and customer-written review text that may enter the agent's working context. This is expected for review handling, but it is sensitive and user-generated content.

Skill content
"reviewerName": "John D.", "reviewerEmail": "john@example.com", ... "body": "The wallpapers are stunning."
Recommendation

Treat review bodies as untrusted customer input, avoid copying customer emails unnecessarily, and do not let review text override user or system instructions.

What this means

Review event data can be sent continuously to a configured server until the webhook is removed.

Why it was flagged

The skill documents registering a webhook that sends review events to an external URL. The artifact also includes a shared secret and signature format, which helps, but the destination and secret remain important trust boundaries.

Skill content
curl -X POST https://api.clawver.store/v1/webhooks ... "url": "https://your-server.com/webhook", "events": ["review.received"], "secret": "your-secret-min-16-chars"
Recommendation

Use only webhook URLs you control, set a strong unique secret, verify signatures, and delete webhooks that are no longer needed.