ClawHub

CF Share

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed Cloudflare tunnel/file-sharing helper, but users must be careful because it can intentionally make selected local ports or files reachable from the internet.

Install only if you intentionally need temporary public Cloudflare links. Approve any global or privileged installs yourself, confirm the exact port or file paths before exposing them, prefer token or basic access for anything non-public, avoid sharing secrets or broad directories, use short TTLs, and stop exposures when finished.

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
92% confidence
Finding
This skill is specifically designed to expose local ports and files to the public internet, but it does not place a prominent up-front warning near the top of the documentation about the security consequences. In an agent context, that omission is dangerous because a user or downstream automation may trigger exposure of sensitive local services or files without appreciating that a temporary public URL creates real external reachability.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation explicitly allows access: "none", which makes the shared resource readable by anyone with the link, but the warning is not prominent or repeated at the point of use. In this skill's context, that is especially risky because it exposes local files or services through a public tunnel, increasing the chance of accidental disclosure of internal apps, documents, tokens, or other sensitive content.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal