SECURITY
87 items
83 posts, 3 tools, 1 guide
HalluSquatting uses hallucinated repo and skill names to deliver promptware to AI coding agents. How the attack works and the harness controls that stop it.
Securing AI coding agents: a practical threat model for prompt injection, sandbox escapes, and hallucinated dependencies, with defenses ranked by effort.
TP-Link Kasa cameras leaked precise home GPS coordinates over unauthenticated UDP for years. How the flaw works, the disclosure timeline, and the second CVE.
Langflow CVE-2026-55255 is the first AI agent platform on CISA's exploited vulnerabilities list. How the IDOR flaw works and how to check if you are exposed.
AI voice fraud needs only three seconds of audio to clone a voice, and detection has failed. The defenses that work and what voice tech builders should change.
Days after getting caught uploading entire codebases to xAI servers, Grok Build is now open source on GitHub. The HN community isn't convinced it's enough.
Cursor 0day: opening a repo on Windows can auto-execute a malicious git.exe. How the flaw works, the 7-month disclosure timeline, and practical mitigations.
Open-source tool gives Claude Code, Codex, and other agents their own isolated Linux VM on your machine - network firewall included, no cloud account required.
GhostLock (CVE-2026-43499) is a 15-year-old Linux kernel use-after-free in rtmutex. How the exploit works, which kernels are affected, and what HN says.
Grok Build CLI wire-level analysis: a researcher found it uploads whole repositories, including .env secrets, to xAI servers. What the captured traffic shows.
Ghost Font hides text in video using motion, so humans can read it but frame-by-frame AI models cannot. How it works and how HN commenters broke it.
GitLost is a prompt injection flaw in GitHub Agentic Workflows that let attackers extract private repo contents via public issues. How the attack works.
An obfuscated bash script on a Uniqlo x Akamai t-shirt, decoded: what the base64 payload does when run, and why HN argues over whether it was AI-generated.
Flipper Zero firmware reaches stable 1.0 and moves to a community contribution model. What changes for contributors and how HN sees official vs custom firmware.
Claude Code request marking: hidden unicode apostrophe and date-format markers flag timezone, domain and lab keywords. What was found and what to do about it.
GLM 5.2 vs Claude Code on Semgrep IDOR benchmarks: the open-weight model scored higher at about one-sixth the cost per finding. Setup, results and HN reactions.
OpenAI June 2026 API updates as an agent control plane: workload identity, Admin APIs, Secure MCP Tunnel, moderation scores, billing and cache retention.
Perplexity Bumblebee: an open source, read-only Go scanner that checks packages, editor extensions and MCP configs against exposure catalogs, with setup steps.
Arcade AI agent authorization explained: what its MCP runtime does, how it differs from rolling your own OAuth, and when it is the right fit.
Filippo Valsorda argues LLMs have made vulnerability reports less special. His case against old coordinated disclosure norms, plus the HN pushback.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.