ClawHub

DeepDive OSINT

Security checks across malware telemetry and agentic risk

Overview

DeepDive OSINT has a coherent investigation purpose, but installing it can automatically fetch and run unpinned GitHub code and dependencies while storing sensitive investigation data locally.

Install only if you are comfortable with a skill that can fetch and run a full GitHub application and pip dependencies on invocation. Review or pin the repository first, run it in a constrained environment, avoid sensitive documents or real API keys until you understand storage and provider data flow, and verify OSINT findings before sharing or acting on them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill instructs automatic cloning of a remote GitHub repository and installation of its Python dependencies at first run via subprocess. This creates a supply-chain and arbitrary code execution risk because unpinned remote code and dependency scripts can execute on the host outside the narrow scope of an OSINT skill.

Context-Inappropriate Capability

Low
Confidence
89% confidence
Finding
The skill directs automatic opening of a generated HTML file through an external launcher (`xdg-open`) after writing investigation output to disk. This is risky because it causes side effects outside the agent's core function, may trigger browser execution of active HTML/JS content, and can expose users to local file handling or browser-based risks without consent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill persists investigation data to disk and auto-opens generated artifacts without prominently warning the user. In an OSINT context, the saved data may contain sensitive research subjects, leads, or derived associations, so undisclosed persistence and file opening materially increase privacy and operational security risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal