zenzap-onboarding

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says—set up a Zenzap workspace—but it gives a plugin/API credentialed access to the new workspace, so users should review that access carefully.

Before installing, confirm you trust the Zenzap plugin source, understand that a real workspace and bot credentials will be created, explicitly approve the invite email and topics, and know how to revoke or rotate the API credentials if needed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

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.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Installing the plugin changes the agent environment and later gives the plugin Zenzap connection credentials.

Why it was flagged

The skill asks the user to install an external plugin, but that plugin's code and provenance are not included in the reviewed artifacts.

Skill content
openclaw plugins install @zenzap-co/openclaw-plugin
Recommendation

Install the plugin only from a trusted source and review its permissions before configuring it.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

The agent or configured plugin can act as the bot inside the Zenzap workspace using these credentials.

Why it was flagged

The skill obtains API credentials for the newly created workspace and instructs the agent/plugin to use them for authentication.

Skill content
"credentials" | **API Key** for Bearer auth, **API Secret** for HMAC-SHA256 signing (store securely), **Control Topic ID**.
Recommendation

Treat the returned API key and secret as sensitive, store them securely, and confirm how to revoke or rotate them.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Workspace events and messages may be routed to the agent through the plugin.

Why it was flagged

The skill establishes an event-routing channel between the Zenzap workspace and the agent/plugin, which is central to the integration but carries workspace messages/events.

Skill content
Once configured, the plugin handles authentication and event routing for you.
Recommendation

Use this only if you want the agent connected to Zenzap events, and verify what event data the plugin receives.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

The agent can create channels in the new workspace after confirmation.

Why it was flagged

The skill can mutate the Zenzap workspace by creating topics, but it explicitly says to wait for user confirmation first.

Skill content
Once confirmed, create each topic: POST https://api.zenzap.co/v2/topics
Recommendation

Confirm the exact topics before allowing creation, especially in a real company workspace.

#
ASI09: Human-Agent Trust Exploitation
Low
What this means

The agent may need to ask for an email separately before creating the workspace and sending an invitation.

Why it was flagged

The listed four questions omit the human email even though the API request schema later marks humanEmail as required, so the data-collection instructions are slightly incomplete.

Skill content
Ask the human these 4 questions before calling the API. Do not assume or infer any answers:
Recommendation

Make sure the agent explicitly asks which email address to invite before submitting the onboarding request.