ClawHub
Back to skill

Security audit

connie

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Connie CRM connector with live workspace access, and I found no hidden local code or deceptive behavior.

Install this only if you want OpenClaw to act in a real Connie workspace using your authorized account. Use the intended workspace during OAuth, confirm record-changing or credit-spending operations before they run, avoid sending unrelated secrets through tool arguments, and revoke the grant when you no longer need it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation description is broad enough to activate on many generic 'Connie workspace' or 'change Connie data' requests, which could cause the agent to select this skill without sufficiently narrowing whether the user intended live CRM actions. Because this skill connects to a real hosted MCP server with read/write access to workspace data, over-triggering increases the chance of unintended data access, modification, export, or credit-consuming operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.