Beam / field notes

What we’re seeing in the field.

What we're seeing as we watch AI coding agents work — flagged actions, skill/MCP scan findings, and how to keep Claude Code, Codex, and the rest honest without slowing them down.Page 11 of 14

All authorsYash ThakkerBeam TeamNewest firstOldest firstTitle A–Z

AllAI AgentsSecurityAI Agent SecuritySupply ChainClaude CodeIncident ResponseThreat IntelligencePrompt InjectionOpenAIMCPAnthropicAgent SecurityCredential TheftAgent SkillsVulnerability ManagementClaimed vs Verified

158 posts

Sep 14, 2026 · 10 min readHow to Stop Codex CLI From Running Dangerous CommandsOpenAI's Codex CLI sandboxes and gates commands by default, but the wrong approval/sandbox combination — or a plain --dangerously-bypass-approvals-and-sandbox flag — removes those guardrails entirely. Here's how the approval policy and sandbox actually work, and how to set safe defaults for a real repo.Sep 14, 2026 · 11 min readHow to Stop Cursor From Running Dangerous CommandsCursor's Agent mode can run real shell commands against your machine. This guide covers Run Modes, the terminalAllowlist in permissions.json, why the old command denylist was deprecated, and how to scope auto-run safely.Sep 14, 2026 · 11 min readHow to Stop Grok From Running Dangerous CommandsxAI's Grok Build CLI ships a permission and sandbox system of its own, but most developers reach Grok through a third-party harness where the model has no say over what runs. Here's how to lock down both cases.Sep 14, 2026 · 14 min readWhat are agent harnesses? And how to stop destructive commandsThe model only ever produces text — it is the harness around it that opens files and runs shell commands. This post defines "agent harness," maps the recurring safety mechanisms across Claude Code, Codex, Cursor, and Grok Build, and explains why observability is a second layer, not a replacement for sandboxing.Sep 14, 2026 · 11 min readWhy Beam is open source: agent safety belongs to everyoneEvery core Beam capability — the local collector, the scan heuristics, the agent hooks, and the security skills collection — is AGPL-3.0 open source you can read and run today. This explains what is open, what is licensed, and the reasoning behind the split.Sep 12, 2026 · 9 min readThe AI agent security market in 2026: sizing, funding, and M&AAnalysts and acquirers are betting that autonomous AI agents need their own security layer, not just another checkbox on a WAF. This roundup ties Gartner's securing-AI forecast to the deals and venture rounds that actually closed in 2025–2026, and names where a local-first coding-agent monitor sits beside enterprise platforms.Sep 12, 2026 · 9 min readAI agent guardrails: monitoring vs. blocking (and where Beam sits)Enterprise AI agent security platforms sell runtime blocking in the API path; NVIDIA OpenShell contains in a sandbox. Beam records on the laptop and lets owners and admins set observe, advisory, or enforce policy — including Sentinel pause/block on browser AI chats. This post names the layers and the remaining limits.Sep 12, 2026 · 12 min readBrowser AI chat risk: what Beam Sentinel checks before you sendDevelopers watch what Claude Code and Cursor do on disk, then paste stack traces and configs into a browser tab without the same guardrails. Beam Sentinel runs the same local heuristic checks on six major chat sites before a prompt leaves the page — and has hard limits worth naming upfront.Sep 12, 2026 · 11 min readCursor vs Claude Code vs Copilot: agent safety comparedThe three dominant AI coding agents do not share the same default posture. This comparison maps run modes, OS sandboxes, MCP approval behavior, and permission files so you can see where confirmation still exists — and where it does not.Sep 12, 2026 · 11 min readRolling out AI coding agents across your team: an IT and security checklistPlatform and security teams get asked to roll out coding agents like any other developer tool — except these tools run shell commands and install MCP servers. This checklist covers identity, device baselines, policy, sandbox defaults, visibility, and the evidence layer auditors expect, without duplicating the compliance-framework essay.Sep 12, 2026 · 13 min readEU AI Act and AI coding agents: timeline, GPAI, and logging for dev teamsSecurity teams ask whether the EU AI Act mandates logging for Cursor, Claude Code, and Copilot. This deep dive maps the official timeline, separates GPAI provider duties from internal dev-tool deployers, and spells out documentation and logging expectations — without duplicating the general audit-trail primer.Sep 12, 2026 · 14 min readThe RubyGems attack: how OpenAI agents abused a package build systemIndependent researchers traced over 2,000 malicious RubyGems packages uploaded in May 2026 back to an OpenAI agent swarm that abused RubyDoc.info's automatic documentation builds to get code execution — an incident OpenAI never disclosed until it was caught. This explains the mechanism and what it means for anyone trusting a package registry's build system.

Page 11 of 14 · 158 posts