ClawHub
Back to skill

Security audit

Yufluent Clawhub Publish Yufluentcn Chat Assist

Security checks across malware telemetry and agentic risk

Overview

The skill appears to support ecommerce replies through a remote Yufluent API, but it handles sensitive customer/order text and bearer tokens with unclear user control and broad activation triggers.

Review before installing. Use this only if you are comfortable sending customer-support text and possible order context to Yufluent, and avoid using it with sensitive customer data unless the API endpoint, retention policy, and authorization-token handling are clear. The publisher should narrow the triggers, disclose the remote data flow, and restrict TOKENAPI_BASE_URL to trusted HTTPS hosts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tainted flow: 'url' from os.getenv (line 271, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Content
}
    if body is not None:
        kwargs["json"] = body
    return requests.post(url, **kwargs)


def _raise_for_status(resp: requests.Response) -> None:
Confidence
91% confidence
Finding
return requests.post(url, **kwargs)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrases are overly broad and map to common customer-service requests like '写个英文回复' or '订单到哪了' without requiring clear ecommerce or platform-specific context. This can cause the skill to activate in unrelated conversations and route user content to the external Yufluent service, increasing the chance of unintended data disclosure or misuse.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script sends buyer message content and optional order context to a remote service via run_skill() without any disclosure, confirmation, or local-only alternative visible in this file. Because these fields can contain personal, order, or support data, transmitting them off-host creates a real privacy and data-handling risk if users are unaware or the backend is not appropriately governed.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.