Skylv Universal Bot Maker

ReviewAudited by ClawScan on May 4, 2026.

Overview

This instruction-only bot builder is coherent with its stated purpose, but users should verify the external npm tooling and carefully protect messaging-platform tokens before using it.

Before installing or using this skill, confirm that the referenced npm packages are legitimate, pin versions where possible, keep bot tokens out of chat and source control, and deploy first to a private test environment with clear stop/rollback steps.

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.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Running an unverified npm CLI or library can execute code on the user's machine or in the generated project.

Why it was flagged

The skill directs users to external npm tooling and a library that are not bundled or pinned in the artifact. This is central to the bot-builder purpose, but package provenance should be checked.

Skill content

npx bot-builder create my-bot ... const { BotBuilder } = require('@skylv/bot-builder');

Recommendation

Verify the npm package owner and source, pin versions, inspect the package before use, and run setup in a disposable project directory when possible.

Medium

#ASI03: Identity and Privilege Abuse

What this means

If these tokens are exposed or over-scoped, someone could control the bot, send messages, or access bot-related platform data.

Why it was flagged

The generated bot configuration uses platform tokens and app secrets. These credentials are expected for bot deployment, but they can grant message-sending and account-level bot authority.

Skill content

token: ${TELEGRAM_BOT_TOKEN} ... token: ${DISCORD_BOT_TOKEN} ... appSecret: ${WECHAT_APP_SECRET}

Recommendation

Use least-privilege bot tokens, store them in a secret manager or environment variables, avoid pasting real secrets into chat, and rotate tokens after testing.

Low

#ASI10: Rogue Agents

What this means

A deployed bot may keep responding to users or sending messages until it is stopped or redeployed.

Why it was flagged

The skill includes deployment paths that run the generated bot as a continuing service. This persistence is expected for a bot, but users should explicitly manage lifecycle and shutdown.

Skill content

await bot.deploy(); ... docker run -d --name my-bot -p 8443:8443 ... vercel deploy

Recommendation

Test in a private sandbox first, review handlers before production deployment, monitor logs, and document how to disable or roll back the bot.

Medium

#ASI07: Insecure Inter-Agent Communication

What this means

Incoming platform messages and user profile data may be processed by the bot and its hosting environment.

Why it was flagged

The bot architecture receives platform webhook traffic and processes user identifiers, names, avatars, and message content. This is expected for messaging bots, but the artifact does not describe validation, retention, or privacy controls.

Skill content

"/telegram/webhook" ... "/discord/webhook" ... "/wechat/webhook" ... user: { id: '123456', name: '张三', avatar: 'https://...' }

Recommendation

Validate webhook origins/signatures where each platform supports it, minimize stored user data, document retention, and avoid logging sensitive messages unnecessarily.