ClawHub
Back to skill

Security audit

Deep Research Pro v2.1

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed deep-research workflow that creates local research files and uses web/API search, with no evidence of hidden or destructive behavior.

Before installing, be comfortable with the skill creating local research artifacts and sending search queries to external research websites/APIs. Use a dedicated project folder, avoid confidential or proprietary topics unless external lookup is acceptable, and delete generated cards or reports when they contain sensitive material.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to create and retain multiple files across several directories as part of its normal workflow, but it does not clearly warn the user up front that persistent filesystem writes will occur or that artifacts may be kept for later reuse. In an agent environment, this can cause unintended storage of sensitive research topics, generated content, or quoted source material, especially because the skill also says generated card files are preserved after interruption.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill requires use of OpenAlex API and web browsing to retrieve external content, but it does not disclose network access, data sharing implications, or any privacy boundary before those actions occur. If a user supplies sensitive or proprietary topics, the agent may transmit queries externally or fetch third-party content without informed consent, creating privacy and compliance risk.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.