Claude API MCP tool-list pinning

General Analysis

Claude API adds MCP tool-list pinning: Review changes before use

Use Claude API MCP tool-list pinning to preserve reviewed definitions, control the first request, and separate schema changes from server authorization.

PLAYBOOK7 min readLatest

Claude Code account sync

General Analysis

Claude Code adds account sync: Review what reaches terminals

Review Claude Code account-synced skills and plugins: compare execution behavior, configure managed opt-outs, and verify removal across terminal sessions.

PLAYBOOK6 min readLatest

Copilot approvals and human review

General Analysis

Copilot can approve pull requests: Preserve required human review

Configure Copilot pull request approvals without losing required human review. Check counting policy, mixed-file changes, stale approvals, and review evidence.

PLAYBOOK6 min readLatest

ChatGPT plugin account boundaries

General Analysis

ChatGPT adds multi-account plugins: Keep actions in the right account

Review ChatGPT multi-account plugin security across credential routing, cached results, write approvals, and source-to-destination data transfers.

PLAYBOOK7 min read

Copilot metrics: What stays hidden

General Analysis

GitHub Copilot adds CLI metrics: Reconcile MCP activity with security evidence

Use Copilot's new CLI customization metrics to investigate MCP activity while preserving reporting gaps, hidden names, and the distinction between connections and actions.

PLAYBOOK7 min read

Plugin4Shell: Check the checkout

General Analysis

Plugin4Shell disclosed: Check coding-agent plugin sources

Respond to Plugin4Shell by checking actual plugin source hosts, deploying verified agent fixes, and reviewing installed copies separately from update settings.

PLAYBOOK7 min read

Claude merges Chat and Cowork

General Analysis

Claude Chat and Cowork merge: Review carried-over permissions

Review retained connectors, folder grants, approval preferences, and cloud tasks after Claude's September 16 Chat–Cowork merger announcement.

PLAYBOOK6 min read

Salesforce in Claude: Review access

General Analysis

Salesforce in Claude beta: Review access before rollout

Review Salesforce in Claude's beta plugin, distinguish its setup from custom MCP connections, and verify user permissions, action approvals, and audit evidence.

PLAYBOOK7 min read

Codex sandbox escapes

General Analysis

Codex sandbox escapes disclosed: Verify both upgrade paths

Respond to the September 15 Codex sandbox disclosures with separate CLI and desktop upgrade checks, helper inventory, and an evidence-based exposure review.

PLAYBOOK6 min read

Claude Managed Agents tool approvals

General Analysis

Claude Managed Agents: Require approval for sensitive tools

Configure Claude Managed Agents tool approvals, separate customer intent from reviewer authority, and recover pending calls without blindly repeating actions.

PLAYBOOK7 min read

Claude account restrictions

General Analysis

Claude account restrictions: Close personal access and old connections

Deploy Claude tenant and connector restrictions, review existing OAuth grants, and verify which account and network paths your Enterprise rollout covers.

PLAYBOOK7 min read

Agents API sandbox lifecycle

General Analysis

OpenAI Agents API: Manage self-hosted sandbox lifecycles

Connect an Agents API self-hosted sandbox, handle reconnects and uncertain tool outcomes, and clean up session state and provider compute without leaving orphaned work.

PLAYBOOK7 min read

Copilot managed permissions

General Analysis

GitHub Copilot managed permissions: Deploy and verify policy

Deploy GitHub Copilot managed permissions, check which users receive them, resolve team and device policy conflicts, and verify approval behavior before rollout.

PLAYBOOK8 min read

Copilot audit evidence

General Analysis

Microsoft 365 Copilot: Collect prompts and reconcile audit logs

Collect Microsoft 365 Copilot prompts and responses through Graph, reconcile them with Purview audit records, and track missing evidence without assuming full coverage.

PLAYBOOK8 min read

Claude ant apply in CI

General Analysis

Claude ant apply in CI: Preserve state when deployments fail

Use Claude ant apply in CI with reviewed plans, scoped workload identity, serialized updates, and a recovery procedure that preserves partial deployment state.

PLAYBOOK7 min read

OWASP LLM Top 10 2026

General Analysis

OWASP LLM Top 10 2026: From Rankings to Runtime Controls

A technical guide to the OWASP LLM Top 10 2026: its evidence-weighted ranking, model-versus-agent boundary, and the controls to verify before release.

FRAMEWORK10 min read

OWASP Agent Control Standard

General Analysis

OWASP Agent Control Standard (ACS): What It Controls and What It Doesn't

A technical guide to the OWASP Agent Control Standard: its Guardian boundary, v0.1 schemas, roadmap gaps, failure modes, and an implementation test plan.

FRAMEWORK8 min read

Claude Code Enterprise Security

General Analysis

Claude Code Enterprise Security Deployment

Enterprise deployment guide for Claude Code security across managed settings, identity, dev containers, proxy controls, MCP, hooks, OpenTelemetry, CI/CD, and governance.

PLAYBOOK24 min read

Control & Observability

General Analysis

Claude Code Control and Observability with OpenTelemetry

Set up Claude Code OpenTelemetry (OTel), lock the collector destination, audit tool and MCP events, and route production telemetry to a SIEM.

PLAYBOOK25 min read

Settings, Permissions & Bash

General Analysis

Claude Code Settings, Permissions, and Bash Tool Security

A practical guide to Claude Code settings, permission rules, Bash tool controls, hooks, MCP allowlists, telemetry, and safe defaults for developer teams.

PLAYBOOK21 min read

Automated Penetration Testing

General Analysis

Best Automated Penetration Testing Platforms in 2026

A practical 2026 buyer guide to automated penetration testing platforms, autonomous pentesting, automated security validation, CTEM, DAST, BAS, and AI security testing.

PLAYBOOK18 min read

AI Security Platforms

General Analysis

Best AI Security Platforms in 2026

Compare AI security platforms by discovery, agent controls, red teaming, runtime protection, and model security, with dated sources and practical buying questions.

PLAYBOOK6 min read

Claude Cowork Security Risks

General Analysis

Security Guidance for Claude Cowork and Risks

Claude Cowork can reach local files, browser sessions, plugins, MCP servers, scheduled tasks, connectors, and approved desktop apps. This guide explains the main Claude Cowork risks and the security controls enterprises should put in place before broad rollout.

PLAYBOOK13 min read

Claude Code Security Best Practices

General Analysis

Anthropic Claude Code Security Best Practices

Security best practices for Anthropic Claude Code across permissions, Bash, hooks, MCP, sandboxing, proxy controls, telemetry, and CI/CD workflows.

PLAYBOOK22 min read

Securing Claude Code

General Analysis

How to Secure Claude Code

A practical enterprise guide to securing Claude Code with permissions, sandboxed Bash, dev containers, managed settings, MCP allowlists, hooks, proxy controls, OpenTelemetry, and CI/CD release gates.

PLAYBOOK22 min read

AI Red Teaming Tools

General Analysis

Best AI Red Teaming and Adversarial Testing Tools in 2026

Compare PyRIT, garak, Inspect, DeepTeam, and commercial AI red teaming tools by use case, evidence, and operating cost. Includes a free evaluation worksheet.

PLAYBOOK9 min read

Securing Coding Agents

General Analysis

How to Secure Coding Agents

A concise summary of the General Analysis technical whitepaper on securing Claude Code, OpenAI Codex, Cursor, Windsurf, Devin, GitHub Copilot, and Claude Cowork.

PLAYBOOK6 min read

Detecting Shadow AI

General Analysis

How to Detect Shadow AI

A practical guide to detecting shadow AI across browser extensions, SWG endpoint agents, network telemetry, SaaS logs, endpoint agents, AI gateways, and MCP gateways.

PLAYBOOK13 min read

MCP Server Security

General Analysis

MCP Server Security: A Threat Model for Agent Tool Supply Chains

MCP servers put executable code, tool schemas, credentials, and agent context in one path. This primary-source threat model covers nine attack classes, current CVEs, and the controls that contain them.

PRIMER16 min read

Claude Cowork vs Claude Code

General Analysis

Claude Cowork vs Claude Code: Security Differences for Enterprise

Claude Cowork and Claude Code share an agentic architecture but ship very different enterprise controls. A primary-source comparison of sandbox, network, audit-log, MCP, and decision-framework differences for security teams.

FRAMEWORK10 min read

Claude Compliance API

General Analysis

How to Audit Claude with the Compliance API

Anthropic's Compliance API exposes activity events, Claude.ai content, organization settings, and supported Cowork and Claude Code session transcripts. This guide explains current coverage, setup, retention, exclusions, and the controls that still need a separate enforcement layer.

PLAYBOOK13 min read

Securing Claude Cowork

General Analysis

How to Secure Claude Cowork

Claude Cowork brings Claude Code-style agentic work to local files, browsers, apps, plugins, and scheduled tasks. Here is how to put a middleman proxy, browser controls, computer-use limits, and enterprise monitoring around it before using it on real work.

PLAYBOOK16 min read

What Is AI Red Teaming?

General Analysis

What Is AI Red Teaming? A Practitioner's Guide

AI red teaming is adversarial testing of AI systems to find exploitable vulnerabilities before attackers do. Learn how it works, key techniques, real exploit examples, and how to implement it.

PRIMER18 min read

What Are AI Guardrails?

General Analysis

What Are AI Guardrails?

A complete guide to AI guardrails: what they are, the eight main types, how they work architecturally, and how to evaluate them for production LLM and agentic deployments.

PRIMER12 min read

OWASP Agentic AI Top 10

General Analysis

OWASP Top 10 for Agentic AI: What Matters Most?

An analytical guide to the OWASP Top 10 for Agentic Applications 2026: what the ten risks are, how they relate to each other, and what they imply for builders of agentic systems.

FRAMEWORK10 min read

AI Guardrails

General Analysis

Best AI Guardrails in 2026: Tools, Architecture, and How to Choose

Compare AI guardrails by control type, deployment, and limitations. Learn how to measure false positives, latency, and policy coverage before choosing a tool.

PLAYBOOK7 min read