ClawHub

Yufluent Clawhub Publish Yufluentcn Review Intel

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed cloud client for analyzing user-provided ecommerce review text, with no hidden persistence or destructive behavior found.

Install only if you trust Yufluent/OpenClaw with the review text and TOKENAPI_KEY. Do not include buyer names, addresses, phone numbers, regulated data, or confidential business data unless approved, and do not set TOKENAPI_BASE_URL unless it points to a trusted endpoint you control.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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)

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The README instructs users to set an API key and send review data to a cloud-backed analysis service, but it provides no warning about protecting the credential, avoiding hardcoding/screenshot leakage, or considering the sensitivity of transmitted review data. This is not an exploit by itself, but it is a genuine security/privacy weakness in operational guidance because users may mishandle secrets or upload sensitive business/customer data without understanding the exposure.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script sends user-provided review text and optional product data to a remote cloud API via run_skill(), but the CLI does not clearly warn users that their input will leave the local machine. This creates a real privacy and data-governance risk, especially if reviews contain sensitive, proprietary, or regulated content and users assume analysis is local.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal