bx

Name: brave-search-skills/bx
Author: brave

Share on X Share on LinkedIn Share on Bluesky

100Critical

The skill executes unauthorized remote code, lacks necessary security constraints for network and file access, and exposes API keys through insecure environment variable handling.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/20/2026

Content InjectionPerception1 finding

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction2 findings

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Namebrave/brave-search-skills/bx

Registrygithub

Version3e088af66eb6

PURLpkg:github/brave/brave-search-skills@3e088af66eb6?skill=bx

Stars152

Installs344

Source

Repository ↗SKILL.md ↗

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

344 installs

Skills.shDocs

npx skills add https://github.com/brave/brave-search-skills

Assessments (5)

AI Agent Traps ↗

Remote code download and execution detectedcriticalcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025

Remote code download and execution detected (seen 2 times in this file at lines 8, 18)

100% confidenceline 8

curl -fsSL https://raw.githubusercontent.com/brave/brave-search-cli/main/scripts/install.sh | sh

Credential exposure via CLI historylowcredential theftAML.T0055AML.T0037LLM02:2025

The documentation suggests using `export BRAVE_SEARCH_API_KEY=YOUR_KEY`, which persists the API key in shell history files (e.g., .bash_history, .zsh_history), making it accessible to other processes or users on the system.

90% confidenceline 22

export BRAVE_SEARCH_API_KEY=YOUR_KEY

Potential for indirect prompt injection via search resultsmediumindirect prompt injection

The skill is designed to feed 'pre-extracted' web content directly into an AI agent's context. If the search results contain malicious instructions (prompt injection), the agent consuming this data may be compromised.

80% confidence

bx "query" --max-tokens 4096

Keyword baiting in descriptionmediumdiscovery abuse

Description contains a long keyword list that may be designed to trigger the skill for unrelated queries.

70% confidence

Missing allowed-tools declarationlowunauthorized tool use

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Undeclared network usagelowunauthorized tool use

Skill contains network access patterns (HTTP requests, socket connections) without declaring network capability in allowed-tools.

60% confidence

Missing licenseinfopolicy violation

Skill does not specify a license field. Specifying a license helps users understand usage terms.

100% confidence

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/brave/brave-search-skills/bx.svg)](https://mondoo.com/ai-agent-security/skills/github/brave/brave-search-skills/bx)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/brave/brave-search-skills/bx"><img src="https://mondoo.com/ai-agent-security/api/badge/github/brave/brave-search-skills/bx.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/brave/brave-search-skills/bx.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow