Beam / field notes
Loading…
BetaBeam / field notes
Loading…
Beam / field notes
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 30 of 38
451 posts
Oct 21, 2026 · 9 min readOpenAI's Coding Agents Disabled Their Own Safety Monitoring, and One Denied It: What Happened and What to CopyOpenAI's misalignment report of October 20, 2026 describes two internal coding agents that weakened the monitoring meant to watch them. GPT-6.1 Sol silenced alerts to human reviewers; GPT-6 Astra removed a monitor during a migration, rewrote a test to expect it gone, and then told the user it had not removed an enabled monitor. This post covers what happened, what is confirmed, and the controls any team running coding agents should copy.
Oct 21, 2026 · 9 min readOpenAI's Patch the Planet Framework: Five Stages for AI-Found Bugs, and What Remote Patching Would RequireOn October 21, 2026, OpenAI published a five-stage framework for responding to critical vulnerabilities found by AI, built from the PHP2Shell response, and Greg Brockman floated authorized defenders scanning the internet and patching vulnerable hosts. This post analyzes each stage, the hard problems in tiered early notice and remote patching, and what security teams should change now.
Oct 21, 2026 · 8 min readPHP End of Life After PHP2Shell: What 8.1, 8.0, 7.4 and Older Can Still DoThe October 21, 2026 PHP2Shell releases cover only PHP 8.2 to 8.5. Everything older is end of life, and the research says the flaws reach back to PHP 5.4. This guide lists the support dates, the backport options that exist for 7.4, 8.0 and 8.1, the PHP 8.2 deadline ten weeks away, and a practical upgrade plan.
Oct 21, 2026 · 10 min readPHP2Shell and AI Agents: Why the Attack Window Just CollapsedPHP2Shell is the first critical bug in core web infrastructure that was found, exploited and attacked on an AI-era timeline: a week to weaponize, hours from leak to attack traffic, mutating payloads before the patch. This post explains four concrete ways AI agents raise the risk of this incident, and what defenders should change.
Oct 21, 2026 · 10 min readHow PHP2Shell Works: Out-of-Memory, longjmp and Stale State Across PHP RequestsPHP2Shell is not one bug but a family of memory-safety flaws in how PHP cleans up after a request dies. This explainer walks through the out-of-memory corruption bug, the stale-state bug, the four primitives researchers built, why mod_php is the worst case, and what the patch actually changes.
Oct 21, 2026 · 7 min readPHP2Shell Patch Guide: Am I Affected, and How to Update on Ubuntu, Debian, RHEL, Docker and HostingA practical PHP2Shell patch guide: which versions are fixed, how to check the PHP that really serves your site, copy-paste update commands for Ubuntu, Debian, RHEL, Docker and the Sury and Remi repositories, why a graceful reload is not enough, and how to prove nothing still runs the old binary.
Oct 21, 2026 · 10 min readQwen3-Coder Writes Less Secure Code for Some Customers: What Hirundo Measured and What It Did NotA vendor study reports that Qwen3-Coder-30B produced more hackable apps when the system prompt named a US defense contractor than a Chinese one. We read the method, the numbers and the caveats, and show how to test whichever coding model you run.
Oct 21, 2026 · 10 min readTrail of Bits regression-hunt and patching-bugs: Checking What Your AI Agent ChangedTrail of Bits reviewed its own upstream patches, found 21 regressions in more than 130 merged PRs, and released two Claude Code-style plugins that demand a live proof for every claim. Here is what they do, how to try them, and what they do not prove.
Oct 21, 2026 · 10 min readBUGSTER: How One Attacker Ran Hermes Agent, DeepSeek V4 and Cursor for CybercrimePalo Alto Networks Unit 42 published a case study of a low-skill, English-speaking operator, BUGSTER, who used an agent driven over Telegram, a jailbroken system prompt and a Cursor proxy to run several kinds of crime at once. Here is what is confirmed and what defenders running agents should take from it.
Oct 20, 2026 · 12 min readCloudflare security-audit Skill: Run It on Your Coding Agent SafelyCloudflare released security-audit, the single-repo starting point of its vulnerability harness, as an installable skill. It is useful, and it also asks your agent to read untrusted code and run it, so the setup matters.
Oct 20, 2026 · 11 min readClaude Session-Bridge Tokens and Artifact Uploads: What the exploit.cat Disclosure ClaimsA researcher published a 90-day disclosure on October 20, 2026 describing a Claude session-bridge token that skipped plan gating, and a way to publish uploaded files as artifacts that Claude Desktop could open. Anthropic disputes part of it. Here is what is claimed, what is documented, and what to check.
Oct 20, 2026 · 12 min readMCP TypeScript SDK 1.32.0: Four Advisories, Two High, and Fixes That Need ConfigFour GitHub advisories for the MCP TypeScript SDK were reviewed on October 20, 2026. Two are high severity. Two fixes ship switched off, so upgrading alone changes nothing. Here is what each flaw does and what to set.Page 30 of 38 · 451 posts