ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Buildchatbot

v1.0.0

BuildChatbot integration. Manage data, records, and automate workflows. Use when the user wants to interact with BuildChatbot data.

⭐ 0· 21·0 current·0 all-time
byMembrane Dev@membranedev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
The skill claims to integrate with BuildChatbot and all runtime instructions revolve around the Membrane CLI and creating a Membrane connection to BuildChatbot, which is a proportionate and expected approach. One minor inconsistency: the SKILL.md lists 'Official docs' pointing to IBM Watson Assistant documentation, which appears to be a copy/paste error and is unrelated to Membrane/BuildChatbot.
ℹ
Instruction Scope
Instructions tell the agent to install and run the Membrane CLI, perform browser-based login, create connections, list actions, run actions, and use Membrane's proxy to call BuildChatbot endpoints. These actions are within the stated purpose. Important: proxying requests via Membrane means request payloads and any data you send will transit (and may be handled) by Membrane's service — the user should understand and consent to that. The SKILL.md otherwise does not instruct reading unrelated files or environment variables.
✓
Install Mechanism
This is an instruction-only skill (no automated install spec). The doc asks users to install @membranehq/cli via npm globally or use npx in one place. That is a normal, low-risk developer action (no obscure downloads or archive extraction), but installing global npm packages affects the host environment and users should verify the package and its source before installing.
✓
Credentials
The skill declares no required env vars or credentials and the instructions rely on Membrane's connection-based auth (browser login). No unrelated secrets or config paths are requested. This is proportionate to the stated functionality.
✓
Persistence & Privilege
The skill is not always-enabled and uses normal autonomous invocation settings. It does not request system-wide configuration changes or elevated persistence. No privilege escalation or cross-skill config modifications are indicated.
Assessment
This skill appears to do what it says: it uses the Membrane CLI to connect to BuildChatbot and run actions. Before installing/using it: 1) Understand that requests and any data you pass will go through Membrane's servers — review Membrane's privacy/security policy and trust boundary before sending sensitive data. 2) Verify the npm package (@membranehq/cli) and the org (membrane) on npm/GitHub before running global installs; prefer using npx or a pinned version instead of -g if you want less system impact. 3) Note the SKILL.md references IBM Watson docs (likely a copy/paste error); confirm the BuildChatbot target and API surface you intend to use. 4) In headless or CI environments, be prepared for the login flow that requires opening a browser or completing a login code. If you need stronger assurances (e.g., company policy compliance), request the upstream repository/package manifest and a privacy/processing statement from the skill author.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fa9d0psfx120dt35x827b79844jgd

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments