ClawHub
Back to skill

Security audit

Google Jules Tools CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for Google Jules CLI sessions, with expected install, login, network, and repository-change risks that users should handle carefully.

Install only if you intend to let your agent use Google Jules. Prefer a normal user-level npm install over sudo, authenticate with the intended Google account, run pulls on a clean branch or disposable clone when possible, and review `git status` and diffs before committing, merging, or deploying any pulled changes.

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 (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to run `jules remote pull --session <session_id>` to retrieve remote code changes, but it does not explicitly warn that this operation can modify the local repository/worktree. In an agent context, pulling remote-generated code into the current checkout can overwrite files, introduce unreviewed changes, or disrupt the user's working state if performed without confirmation and isolation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal