TheRoaster

PassAudited by ClawScan on May 1, 2026.

Overview

The skill appears to be a coherent roast-generation API, but optional paid use involves wallet transactions/API keys and the roast input is sent to an external service.

This skill is reasonable to install if you are comfortable using a remote roast-generation service. Treat paid-plan actions carefully: never let an agent auto-sign wallet transactions, verify the exact USDC amount and contract before approval, protect any API key, and avoid sending private or sensitive content for roasting.

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

If the paid flow is used, the user could authorize an on-chain payment for API credits.

Why it was flagged

The skill documents agent-accessible transaction-building and purchase flows, which can lead to real USDC spending, but it also states wallet use must require human confirmation.

Skill content
Agents can: ... Build transactions via /api/v1/tx/* ... Purchase directly using a wallet they control ... Agents must never call use any wallet functions without human confirmation.
Recommendation

Use the free tier unless paid quota is needed; before signing or sending any transaction, verify the chain, contract, recipient, tier, duration, and USDC amount.

What this means

A leaked API key could consume the user's paid quota, and wallet signatures link the user's wallet address to the service.

Why it was flagged

Paid use requires wallet-based authentication and an API key, which are expected for this service but still represent account and quota-bearing credentials.

Skill content
Auth claim (issue API key if entitled): ... "address": "0xYourWallet", "signature": "0xSignedMessage" ... API keys are issued once and never shown again
Recommendation

Sign only the expected authentication nonce, store the API key securely, and do not paste keys or signatures into unrelated chats or tools.

What this means

Text submitted for roasting may be processed by theroaster.app and potentially OpenAI, so private or sensitive content could leave the user's environment.

Why it was flagged

The skill sends user-supplied social content to a remote API, and the service documentation says a third-party provider is used to generate roasts.

Skill content
POST https://theroaster.app/api/v1/roast ... Body JSON: { "requester": "ClawdClawderberg", "name": "SomeMolty", "message": "I think this is a great idea" } ... OpenAI API provides roasts
Recommendation

Avoid sending confidential, personal, or non-public messages to the roast endpoint unless the service's privacy practices are acceptable.

What this means

Users have less registry-level information for independently validating who operates the service before trusting it with payments or API usage.

Why it was flagged

The registry metadata does not provide a source repository or homepage, which limits provenance review for a remote API service that also offers paid on-chain access.

Skill content
Source: unknown; Homepage: none
Recommendation

Verify the service domain, contract address, pricing, and operator reputation before purchasing a plan or relying on it for production bots.