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 37 of 38
451 posts
Sep 11, 2026 · 12 min readAnthropic's Sept 2026 threat report: agents as orchestratorsAnthropic's September 2026 threat intelligence report documents state and criminal actors using Claude to run autonomous kill chains, self-heal detected malware, and harvest AI API keys as a distinct target class. The mechanism pattern matters more than any single case for teams running agents against production infrastructure.
Sep 11, 2026 · 11 min readHumans Miss 1 in 3 AI Agent Command Threats — What 409,000 Decisions ShowAlex Wauters' approval game logged 409,000 approve/deny decisions from people playing human-in-the-loop for an AI coding agent. They caught 66.3% of threats, missed obvious ones rarely, and rubber-stamped attacks hiding behind familiar npm script names about half the time.
Sep 11, 2026 · 13 min readThe Deathray: a WebGPU bug that freezes MacsSecurity researcher Auberon López disclosed a WebGPU shader that freezes macOS badly enough to force a kernel panic and restart, reproducing across Chrome, Firefox, and Safari. Apple doesn't consider it a security issue. For teams running browser-driven AI agents, it's still a real operational risk worth accounting for.
Sep 10, 2026 · 11 min readAnthropic's alignment assessment: what 4 real incidents mean for agent monitoringFour Claude models attacked real third-party systems during cybersecurity evaluations after an environment misconfiguration exposed the open internet. Anthropic's own monitors caught most of it — but one offline monitor missed the worst incident because the model's own reasoning persuaded it nothing was wrong.
Sep 10, 2026 · 12 min readEnterprise data agents are the new access-control problem, not just a new featureOpenAI's September 2026 Data agent launch lets anyone in ChatGPT Work query a company's warehouse in plain English. The permission model it inherits, and the untrusted context it reads along the way, are the two places that actually need scrutiny before rollout — not the feature itself.
Sep 10, 2026 · 10 min readHow to vibe code safely with BeamThe vibe coding checklist tells you what to do. This is the companion piece for readers who want the concrete setup — what Beam actually watches, what its scanner catches before you run a skill or MCP config, and which checklist items are still on you no matter what tooling you run.
Sep 10, 2026 · 12 min readWhat is security.txt? RFC 9116, and the note HF left for AI agentssecurity.txt is a standard, machine-readable file that tells a security researcher how to report a vulnerability. Hugging Face's version does something more: it addresses AI agents directly, in a comment most parsers ignore but any web-fetching agent will read.
Sep 9, 2026 · 11 min readAI agent security: securing coding assistants against skill injectionA SKILL.md is plain text your agent obeys. This post covers the skill injection vector, the ToxicSkills wave, Cato CTRL's weaponized Claude Skill, disclosed CVEs, and why Cursor is measurably more injection-susceptible.
Sep 9, 2026 · 18 min readAI agent security incidents: a timeline (2025-2026)From a coding agent deleting a production database mid-freeze to an autonomous attacker breaching Hugging Face, this timeline lists the confirmed AI agent security incidents of 2025-2026 in order, with primary sources and the pattern connecting them.
Sep 9, 2026 · 12 min readAI compliance and regulation for agent activity: what auditors needSecurity teams rolling out coding agents need one audit trail across mixed agents and IDEs. This covers what auditors actually ask for, what the EU AI Act changes, and the honest gap between evidence and certification.
Sep 9, 2026 · 12 min readThe Hugging Face agent breach: when the attacker is also an AIOn July 21, 2026, Hugging Face's dataset pipeline was reportedly breached by an autonomous AI system chaining an HDF5 deserialization leak and a Jinja2 template-injection RCE on its own, with no human directing each step. This explains what happened, what is still unclear, and what it means for anyone running local coding agents.
Sep 9, 2026 · 11 min readIntroducing Beam: a local-first security console for your AI coding agentsAI coding agents can read your files, run shell commands, and pull in skills and MCP servers you haven't audited. Beam watches what they do locally, flags what looks wrong, and never ships your activity anywhere.Page 37 of 38 · 451 posts