Permissions
18 articles about permissions.
Third-Party Apps: What They Are, How Permissions Work, and Security Risks
A complete guide to third-party apps covering what they are, how they access your data through OAuth and APIs, common security risks, and how to audit and manage permissions across platforms.
AI Agent Blast Radius: What It Is and How to Measure It
AI agent blast radius defines the maximum damage an agent can cause in a single failure. Learn how to measure, categorize, and reduce blast radius across desktop, cloud, and code agents.
AI Agent Trust Management: A Practical Framework for Production Systems
How to manage trust in AI agents across their lifecycle, from initial deployment with minimal permissions to earning expanded access through verified behavior.
How to Limit the Blast Radius of a Compromised AI Agent
Practical techniques to contain damage when an AI agent gets compromised. Covers process isolation, least-privilege tooling, network segmentation, and real
93% No Scope. 0% Revocation.
Most agent integrations request broad permissions with no mechanism for revocation. No scope and no revocation is a terrifying combination.
Auto-Approving Read-Only Commands in AI Coding Agents with Hooks
How to set up permission tiers and hooks that auto-approve safe read-only commands in AI agents while keeping destructive operations gated behind manual
v2.1.78 Broke bypassPermissions: Skills Are User Content
When bypassPermissions broke, it revealed that .claude/skills/ files are user content, not system files. Agent permission models need to respect this boundary.
Mapping AI Agent Permissions in Cloud with Graph-Based Inventories
How Cartography and graph-based tools map AI agent permissions, blast radius, and access patterns across AWS, GCP, and Azure before a security incident forces you to.
The Sandbox Paradox: AI Agents Need Access to Be Useful
AI agents need system access to be useful but restrictions to be safe. The sandbox paradox is the central tension in desktop agent design - here's how to
YOLO Mode vs Explicit Approval - When to Let AI Agents Run Freely
When should you skip permissions for AI agents? The answer depends on reversibility. Git repos are safe to YOLO, but email and messaging need explicit
Yolo Mode vs Safe Permissions - When to Let Your AI Agent Run Free
Should you skip permission checks in AI agents? It depends on the task. Code agents with git are low risk. Desktop agents touching production systems need
Zero-Trust Security for AI Agents: When Default Deny Goes Too Far
Zero-trust security models applied to AI agents can make them useless if too aggressive. Learn how to balance security with agent usefulness in production
AI Agent Failure Rates and the Desktop Permissions Problem
AI agents fail more often than people think. When desktop agents can click anything and type anywhere, one hallucinated action can send emails or delete files.
The Asymmetric Trust Problem - When Your AI Agent Has More Access Than You Intended
Granting macOS accessibility permissions to an AI agent gives it access to every text field, password manager value, and bank balance visible on screen. The permission you think you granted is a small subset of what you actually granted.
The Boundary Tax - The Cost of Setting Limits in AI Agent-Human Relationships
Every boundary in an AI agent-human relationship has a cost. Learn about the boundary tax and how to balance safety with productivity in desktop automation.
Bypass Permissions vs Allowlists - Finding the Middle Ground for AI Agents
Full permission bypass is reckless and full approval mode is unusable. The middle ground with allowlists is where AI agent permissions actually work.
Designing a Tiered Permission System for AI Desktop Agents
Full YOLO mode is dangerous and full approval mode is unusable. Tiered permissions with allowlists per action type hit the sweet spot.
AI Agent Permissions - Why Local Agents Do Not Have the Cloud Permission Problem
Cloud AI agents like Cowork need folder-level access grants that linger after tasks complete. Local agents that use accessibility APIs avoid this entirely.