ClawHub
Back to skill

Security audit

Openclaw Perfexcrm Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PerfexCRM API helper, with broad but disclosed CRM read/write capability and no hidden execution or persistence found.

Install only with a PerfexCRM API key scoped to the operations you want the agent to perform. Treat customer, invoice, ticket, staff, and payment data as sensitive, avoid exposing the API key in chat logs or shell history, and require confirmation for deletes or other high-impact CRM 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises broad CRM access and includes examples for listing, creating, updating, assigning, and deleting business records, but it does not prominently warn that these operations affect live production data and may expose sensitive customer, billing, and support information. In conversational-agent use, that omission increases the chance of accidental destructive actions or inappropriate disclosure because users may treat the skill as informational rather than operational.

External Transmission

Medium
Category
Data Exfiltration
Content
**List all customers:**
```bash
curl -s -H "X-API-KEY: $PERFEXCRM_API_KEY" "$PERFEXCRM_API_URL/customers"
```

**Search customers:**
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The environment setup instructs users to export an API key but does not warn that the credential is sensitive, grants CRM access, and must not be logged, shared, or embedded in prompts and transcripts. In messaging-agent contexts, omission of credential-handling guidance raises the risk of accidental secret exposure through chat history, shell history, screenshots, or debug output.

Static analysis

No suspicious patterns detected.