SMBcrm CRM & Marketing Platform

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: smbcrm Version: 0.1.0 The skill bundle provides legitimate documentation and operational instructions for an AI agent to assist with SMBcrm (Small Business CRM) integrations. The SKILL.md file contains helpful implementation patterns, security best practices (such as token rotation and least-privilege access), and standard API usage examples for endpoints like services.smbcrm.com. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found.

Findings (0)

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 a Private Integration Token is over-scoped or exposed, someone could access or change SMBcrm account data.

Why it was flagged

The skill explicitly guides use of bearer tokens for SMBcrm API authentication. This is expected for the stated purpose, but those tokens can grant account access.

Skill content
Private Integration Token — bearer token for API authentication (created under Settings → Private Integrations)
Recommendation

Use least-privilege tokens, avoid pasting secrets unless necessary, store tokens securely, and revoke or rotate any token that may have been exposed.

What this means

Incorrect API requests or workflow steps could modify or delete contacts, tasks, campaigns, or other CRM records.

Why it was flagged

The skill documents API areas that can mutate CRM records. This is purpose-aligned API guidance, but generated API calls or workflows could have real business impact if run without review.

Skill content
Contacts | Create, read, update, delete, upsert, search, notes, tasks, tags, campaigns, workflows, followers, appointments
Recommendation

Review generated requests before running them, test in a safe account or with limited data first, and follow the skill’s own recommendation to include a test plan and rollback path.

What this means

A broadly authorized MCP or AI assistant setup could expose or change CRM data through connected tools.

Why it was flagged

The skill includes MCP-based AI tool access to SMBcrm. This is disclosed and relevant to the skill, but AI-client/tool connections need clear authentication and permission boundaries.

Skill content
MCP — the AI tool layer that lets compatible clients call SMBcrm tools over HTTP
Recommendation

Limit MCP and Agent Studio permissions to the minimum needed, verify client identity and endpoint configuration, and avoid sharing broad CRM tokens with untrusted clients.