ClawHub
Back to skill

Security audit

agentconcierge

Security checks for vulnerabilities and agentic risk

Overview

This skill appears coherent and purpose-aligned, but users should know their recommendation details are sent to AgentConcierge.

Install only if you are comfortable sending the role, pain point, current tools, budget, and team-size details you provide to agentconcierge.io. Use generalized descriptions for sensitive workflows, and do not include passwords, secrets, private customer data, regulated personal data, or confidential internal plans.

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 (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly states that OpenClaw sends user workflow/profile information to the external AgentConcierge service, but it does not clearly warn users what data may be transmitted, retained, or processed by that third party. This creates a privacy and data-handling risk because users may include sensitive business context, tools, budgets, or operational details in prompts without informed consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly collects user workflow details such as role, pain point, tools, budget, and team size, then sends them to a third-party API without any user-facing notice or consent step. While these fields are not necessarily highly sensitive on their own, they can reveal business operations, tooling stack, budget constraints, and internal needs, creating a privacy and data-sharing risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The API reference instructs clients to send potentially sensitive business-context data such as job role, pain points, tools, budget, and team size to a third-party remote endpoint with no authentication requirement and no accompanying privacy, consent, retention, or sharing disclosures. In a recommendation skill, this context can reveal internal operational challenges, software stack, and spending capacity, creating unnecessary privacy and profiling risk if users are not clearly warned before transmission.

External Transmission

Medium
Category
Data Exfiltration
Content
## API Call

```bash
curl -s -X POST https://agentconcierge.io/api/recommend \
  -H "Content-Type: application/json" \
  -d '{
    "role": "Sales / Business Development",
Confidence
97% confidence
Finding
The skill performs an outbound POST request to an external service using user-supplied content. External transmission is expected for this skill's functionality, but it still represents a real security/privacy concern because organizational context provided by the user is sent off-platform without any explicit warning, consent, or sanitization guidance.

Static analysis

No suspicious patterns detected.