ClawHub

Code Share

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises by sharing code through GitHub Gist, but users should review content because it uploads files to GitHub.

Install this only if you want code to be shared through GitHub Gist. Confirm gh is logged into the intended GitHub account, review files for secrets or proprietary content before upload, and remember that secret Gists are external URLs, not private local storage.

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 instructs the agent to upload code to GitHub Gist, which sends potentially sensitive code or metadata outside the local environment, but it does not require an explicit user-facing warning or confirmation at the point of exfiltration. Even with a sensitive-data scan and secret-gist default, users may not realize their code is being transmitted to a third-party service, creating privacy, confidentiality, and compliance risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script transmits a local file to GitHub Gist, which is an external service, but it does not present any explicit warning, confirmation, or safeguards about possible data disclosure before upload. In an agent skill context, this is risky because the file path and content may originate from broader workflow state or user-provided artifacts, and users may not realize that sensitive code, credentials, or private data are being published or stored outside the current environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal