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 7 of 21

All authorsYash ThakkerBeam TeamNewest firstOldest firstTitle A–Z

AllAI AgentsSecurityThreat IntelligenceSupply ChainIncident ResponseAI Agent SecurityClaude CodeAgent SecurityPrompt InjectionCredential TheftMCPOpenAIAnthropicVulnerabilityClaimed vs VerifiedCodex

251 posts

Oct 28, 2026 · 7 min readApple iOS 27.2 Fixes 163 Vulnerabilities: WebKit Code Execution, Two Sandbox Escapes and What to UpdateApple shipped iOS 27.2 and iPadOS 27.2 on October 26, 2026 with fixes for 163 vulnerabilities. Eight WebKit bugs allow code execution from a crafted page and two let web code leave its sandbox. Apple reports no exploitation, but the advisory is public, so the patch should not wait.Oct 28, 2026 · 10 min readCisco Project Quarry: Open-Source Session-Level Rules for Detecting Rogue AI AgentsCisco has open sourced Project Quarry, a behavior detection engine with Claude Code and Codex plugins that evaluates entire agent sessions rather than single prompts. Here is what is documented, what is not yet, and how it compares with hook-based tools like Beam.Oct 28, 2026 · 10 min readCyberStrikeAI: How 44 AI Agents Probed 19 Organizations in JapanTrendAI researchers reconstructed an October 2026 campaign from attacker-side open directories: an open-source pentest platform, CyberStrikeAI, split recon, exploitation, persistence and exfiltration across 44 agents. Most targets were only probed, but the pattern matters for anyone who runs agents.Oct 28, 2026 · 7 min readPrivate GitHub Repos Deleted by Non-Members: Reports, Claimed vs Verified, and How It Could HappenA company says someone with no membership, invite or role in its GitHub org deleted a private repository, and it cannot be restored. It is not the first such report. The audit log screenshot shows a gh CLI call using an OAuth token. Here is what is established, what is guesswork, and what to check in your own org.Oct 28, 2026 · 10 min readOWASP LLM Exploit Generation Phase 2: A Low-Skill Operator Took Over an Admin Account With ChatGPTThe OWASP GenAI Security Project compared a chat-guided novice with nine autonomous agent setups on live Hack The Box machines. The novice took over an admin account; no autonomous run finished the job. Here is what that means for people who run coding agents.Oct 28, 2026 · 11 min readPHP2Shell and Fragnesia: AI-Assisted Campaign Roots 25 FirewallsDream Research found a toolkit that chained a custom PHP2Shell exploit with the Fragnesia kernel bug to root 25 firewalls, including a US government-affiliated network. Claude Code and an AI offensive platform were on the attacker infrastructure. This post separates what is evidenced from what is inferred.Oct 28, 2026 · 12 min readPoisoned Repo Hooks: How a Worm Armed 42 GitHub Repos Against Claude, Gemini and Cursor UsersA Miasma-family npm worm called testmetest planted auto-run hook files in 42 real GitHub repositories. Opening one in Claude Code, Gemini CLI, Cursor or VS Code can run a hidden 13 MB payload. Here is the chain, the indicators and the checks.Oct 28, 2026 · 11 min readvLLM 0.32.0: Eight Advisories, Including SHM Pickle RCE and an EPS Ghostscript ChainvLLM published eight advisories, fixed in 0.32.0 and listed in the GitHub Advisory Database on October 28, 2026. Two are high severity: a forged shared-memory handle that reaches pickle.loads in the worker, and an EPS image that can reach a vulnerable Ghostscript. The other six are denial-of-service and exposure bugs.Oct 28, 2026 · 8 min readZero Breach Toolkit: What the Free Spyware Scanner Does, and How to Vet It Before You Run ItA free scanner for known mercenary spyware went viral on October 28, 2026. We read the repository instead of the thread. Here is what it checks, where the announcement and the documentation differ, and how to vet any script before you run it.Oct 27, 2026 · 11 min readAI Hacker Cipher Found Four EPICS Base Bugs in 3 Hours 49 Minutes: What Is VerifiedOn October 27, 2026 CISA published four EPICS Base vulnerabilities credited to Cipher, an autonomous agent from Causal Security. The CVEs and the fix are confirmed by CISA. The speed claim comes from the vendor via The Register. Here is the split, and what an agent-speed disclosure means for people who run agents.Oct 27, 2026 · 10 min readAokigahara Infostealer: It Targets Claude Code, Codex and Cursor CredentialsCheck Point Research published an analysis of Aokigahara, a Windows infostealer whose aisessions module goes after the local auth and settings files of Claude Code, Codex, ChatGPT Desktop, Cursor and other AI tools. Here is how it works and what to rotate.Oct 27, 2026 · 7 min readBlack October 2026: The Week of Oct 19-25 Day by Day, and What Is VerifiedA widely shared weekly summary calls the last seven days "Black October": Cairn agents, PHP and Node.js patches, GitLab RCE, Railway, Quest and GMO. We lay out the timeline, mark which claims Beam has verified, and list what a developer running coding agents should change now.

Page 7 of 21 · 251 posts