ClawHub
Back to skill

Security audit

SMBcrm CRM & Marketing Platform

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style SMBcrm integration skill with disclosed API and token guidance, not a hidden executable or persistence mechanism.

Install only if you intend to use SMBcrm advanced integrations. Because the skill can help configure tokens, MCP clients, webhooks, and CRM write workflows, use least-privilege Private Integration Tokens, keep production and test tokens separate, review any generated curl commands before running them, and be especially careful with payments, invoices, public posting, and bulk contact changes.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 237)May include surrounding context.

Start with a simple read request before attempting writes.

bash
curl --request GET \
  --url "https://services.smbcrm.com/locations/<LOCATION_ID>" \
  --header "Authorization: Bearer <PRIVATE_INTEGRATION_TOKEN>" \
  --header "Accept: application/json" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 492)May include surrounding context.

Example: execute an agent

bash
curl --request POST \
  --url "https://services.smbcrm.com/agent-studio/public-api/agents/<AGENT_ID>/execute" \
  --header "Authorization: Bearer <PRIVATE_INTEGRATION_TOKEN>" \
  --header "Content-Type: application/json" \

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 640)May include surrounding context.

md
- Do not default to public app / marketplace guidance
- Do not tell users to use deprecated list endpoints when search endpoints are better
- Do not recommend legacy API v1 for new or existing integrations
- Do not assume duplicate-contact behavior without checking settings
- Do not skip test plans for automations that touch customers or revenue
- Do not recommend OAuth for customer-built SMBcrm automations — use Private Integration Tokens