Security

17 articles about security.

Why Your AI Agent Needs a Firewall - And Why It Should Be Open Source

·2 min read

AI coding agents access your file system, network, and APIs. An open-source firewall lets you audit exactly what the agent can do. Transparency beats trust.

firewallopen-sourceai-agentsecuritytransparency

Privacy Controls Are the Real Story in AI Agent Frameworks

·2 min read

Most agent frameworks let the model do whatever it wants. Privacy-first agents run everything locally, never send screen data to the cloud, and give users explicit control over what the agent can access.

privacyai-agentlocal-firstcontrolssecurity

AI Desktop Agent Security Best Practices for Teams and Enterprises

·10 min read

Giving AI agents access to your computer raises real security questions. Here are the best practices for deploying desktop agents safely - from permission models to data governance.

securityenterpriseai-agentsbest-practicescompliance

The Asymmetric Trust Problem - When Your AI Agent Has More Access Than You Intended

·3 min read

Accessibility APIs were designed for screen readers and expose everything on screen. When you grant an AI agent accessibility permissions, it gets far more access than you probably realized.

trustpermissionsaccessibility-apisecurityai-agent

Blast Radius - What Happens When Your AI Agent Gets Compromised

·2 min read

MCP servers limit blast radius by design with UI-only access, no shell, no filesystem. But in practice, both tools often run in the same session. Here is how to assess the real risk.

securityai-agentblast-radiusmcptrust-boundary

Bypass Permissions vs Allowlists - Finding the Middle Ground for AI Agents

·2 min read

Full permission bypass is reckless and full approval mode is unusable. The middle ground with allowlists is where AI agent permissions actually work.

ai-agentspermissionssecuritydeveloper-experiencedesktop-automation

Why Community Skill Repos Need Platform-Level Sandboxing

·2 min read

Community skills repos are an open attack vector for AI agents. Platform-level sandboxing and verification are essential to prevent supply chain attacks.

securityskillssandboxingsupply-chainai-agents

Cron Jobs and Unsupervised Root Access - The Security Risk of Scheduled AI Agents

·3 min read

Why scheduled autonomous AI agent tasks need audit trails, rate limits, and human review. The security implications of launchd agents running unsupervised with system access.

cron-jobsai-agentsecuritylaunchdautonomous-agentsrate-limiting

Using macOS Keychain for AI Agent Credential Access

·2 min read

Store passwords in macOS Keychain for your AI agent instead of .env files. It is more secure, centralized, and eliminates token pasting across sessions.

macoskeychaincredentialssecurityai-agents

MEMORY.md as an Injection Vector - The Security Risk of Implicitly Trusted Config Files

·2 min read

CLAUDE.md and MEMORY.md files are loaded every session and trusted implicitly by AI agents. This makes them a potential prompt injection vector that most setups do not protect against.

securityprompt-injectionmemoryclaude-mdconfig-filesai-agent

Your AI Agent Shouldn't Send Screen Recordings to the Cloud

·2 min read

Some agents capture your screen and send it to cloud servers for processing. Local agents process everything on device - your data never leaves your machine.

screen-recordingscloudprivacyon-devicesecurity

Why Self-Hosting AI Matters: Your Agent Sees Your Emails, Documents, and Browsing History

·2 min read

AI agents interact with your most sensitive data - emails, documents, browsing history. Self-hosting with local LLMs keeps that data on your machine where it belongs.

privacyself-hostinglocal-llmai-agentssecurity

The Auth Problem for AI Agents - OAuth, Rate Limiting, and Dry Run Modes

·3 min read

AI agents face unique authentication challenges: automating OAuth browser flows, managing rate limits across multiple instances, and testing with dry run modes.

authenticationoauthai-agentrate-limitingsecurity

Why Local-First AI Agents Are the Future (And Why It Matters for Your Privacy)

·14 min read

AI agents that control your computer need access to everything on your screen. Here is why where that data gets processed - locally or in the cloud - is the most important question you should be asking.

privacylocal-firstai-agentssecuritythought-leadership

How to Keep Your .env Files Safe from AI Coding Agents

·2 min read

AI agents that can read and edit files will eventually stumble into your secrets. Here is how to use .claudeignore and macOS Keychain to keep API keys out of the context window.

securitysecretsclaude-codedeveloper-toolsbest-practices

AI Agent Permissions - Why Local Agents Do Not Have the Cloud Permission Problem

·3 min read

Cloud AI agents like Cowork need folder-level access grants that linger after tasks complete. Local agents that use accessibility APIs avoid this entirely.

permissionssecuritylocal-firstcloud-agentscomparison

Prompt Injection and AI Agents - Why Browser-Based Agents Have a Bigger Attack Surface

·3 min read

AI agents that run inside the browser inherit whatever the page feeds them, including injection payloads. Native agents that interact from outside have a smaller attack surface.

securityprompt-injectionbrowser-agentsnative-agentsai-safety

Browse by Topic