ClawHub
Back to skill

Security audit

Clawcrm

Security checks for vulnerabilities and agentic risk

Overview

This CRM skill is not deceptive, but it gives an agent broad autonomous sales, enrichment, and email-sending authority without enough privacy, consent, or token-handling guidance.

Review this skill before installing if you will let an agent run it autonomously. Use it only with authorized lead data, configure clear human approval rules for outreach, verify compliance requirements for sales emails, and store the ClawCRM token in a secret manager or environment variable rather than prompts, logs, or shell history.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages autonomous lead enrichment and sales workflow execution using third-party sources and outbound communications, but it provides no warning that personal and business data will be transmitted to external services. In an agent context, that omission can cause operators to unknowingly process PII or sensitive business data without consent checks, policy review, or data-minimization controls.

Content

No source excerpt is available for this finding.

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 49)May include surrounding context.

1. Sign Up Your Human

bash
curl -X POST https://readycrm.netlify.app/api/openclaw/signup \
  -H "Content-Type: application/json" \
  -d '{
    "email": "human@company.com",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The setup flow shows an admin token being returned and then reused in requests, but it gives no credential-handling guidance such as secure storage, redaction, rotation, or prohibition on logging. Because the token appears to grant administrative access to CRM operations, accidental exposure in prompts, terminal history, chat logs, or agent memory could enable unauthorized access and bulk actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The email-sequence feature enables autonomous outbound messaging with delayed follow-ups, yet the skill does not warn about user impact, consent, rate limits, or legal/compliance obligations. In an autonomous agent setting, this can lead to spam, accidental harassment, reputational harm, or policy violations at scale if the agent sends messages without human review or recipient authorization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.