ClawHub

Yutori research

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Yutori cloud research integration, but users should treat prompts, URLs, and browsing tasks as data sent to Yutori.

Install only if you intend to use Yutori’s cloud service for research or browsing. Use a limited Yutori API key, verify YUTORI_API_BASE points to the intended dev or production endpoint, avoid sending confidential/internal URLs or secrets unless approved, and confirm before form submission or other state-changing browsing tasks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
75% confidence
Finding
The skill’s trigger language is broad enough to capture many ordinary web-related requests without clearly constraining when the external Yutori service should be used instead of local tools. This can cause unintended routing of user tasks and data to a third-party cloud service, increasing privacy and data-handling risk even if the capability is legitimate.

Missing User Warnings

High
Confidence
95% confidence
Finding
The documentation instructs use of cloud research and browsing services but does not warn that prompts, target URLs, extracted content, and possibly sensitive page data will be transmitted to an external provider. Without explicit disclosure and consent, users may unknowingly expose confidential or regulated information to third-party infrastructure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal