ClawHub
Back to skill

Security audit

Zalo CRM & Chatwoot Sync (Zalo-Flow)

Security checks for vulnerabilities and agentic risk

Overview

The advertised CRM functions fit the skill’s purpose, but account routing and controls for bulk messaging need clarification before use.

Before connecting a real account, verify the intended API host and whether the examples are demonstrations. Do not substitute a real token until that is clear. Require approval of recipients and message content before each broadcast, and confirm how queued campaigns can be stopped.

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 (1)

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 28)May include surrounding context.

1. Fetch Conversations Filtered with CRM Tags

bash
curl -s -H "Authorization: Bearer demo" "https://aizalo.com/api/conversations?limit=20"

2. Enqueue Tag-Based Broadcast Campaign

Static analysis

No suspicious patterns detected.