HSTS: How a Single Header Tells Browsers to Stop Asking
How the Strict-Transport-Security header turns one HTTPS visit into a standing rule to use only HTTPS for as long as max-age lasts.
Topic · 134 stories · page 3 of 6
134 stories tagged security on AI Tamer, newest first.
How the Strict-Transport-Security header turns one HTTPS visit into a standing rule to use only HTTPS for as long as max-age lasts.
VOLTA sends stolen data to OpenRouter for a ranked target assessment, with a model fallback chain built for refusals. What defenders can check today.
Wiz ties breaches at OpenCode, Railway, Warp, Northflank and five more to LLMjacking. One stolen key made 800,000 Bedrock calls in 30 hours.
CVE-2026-116366 is rated 9.5 under CVSS 4.0. Fixed in four ClickHouse lines; Cloud is patched. Langfuse pinned its compose file. What to upgrade.
How the WebSocket Upgrade handshake proves a server actually understands the protocol, and why client-to-server frames are XOR-masked even over TLS.
AIR says a top-ranked fake Solana starter kit had one install step that dropped NetSupport Manager on Windows. The signs to check if you ran it.
A forwarded SSH agent can be used by anyone able to bypass permissions on its socket. ProxyJump reaches the inner server over a TCP forward with no agent needed.
yoagent 0.26.0 keeps MCP HTTP redirects on the server's origin so custom key headers stay put; 0.26.1 keeps URL keys out of error text.
Symantec found a relay service that rewrites Codex and Claude Code config files to route traffic through its servers with sandboxing disabled.
Radware found one-day campaign items in repos such as Trivy, LangExtract and MLflow. Two runs show the injected command executed in GitHub Actions.
LanceDB's Python SDK no longer runs remote model code or calls endpoints named in a table's metadata unless your process approves them.
Eight changes from our past week for people building with AI: two security fixes, a new default, a hosted shutdown and new tools, each with a next step.
Security lab Irregular says Z.ai's GLM-5.3 refused none of its offensive tasks and finished 3 of 13 multi-stage attack scenarios in simulated networks.
Quarry checks whole agent sessions, not single prompts, for risky sequences like a credential read followed by an upload. Apache-2.0, with a CLI and SDK.
CISA advisory ICSA-26-300-01 lists four EPICS Base bugs, one rated 9.8, reported by Causal Security's Cipher agent. Update to 7.0.11 from the release tarball.
An unreleased Anthropic model wrote five working attack chains. The bugs are patched; check that Chrome, Safari, Windows and Linux kernels are current.
Gemini 4 Carbon is now open to paying developers, enterprises and AI Ultra users at $2/$10 through 30 November, then $4/$20. Cyber defenders got it first.
At Oracle AI World, Oracle announced AI Workspace for ChatGPT, App Composer with Codex, AI Security Mesh using OpenAI cyber models, and an SMB bundle.
A Moderate GHSA in the Rust inference engine: for qwen-xml and gemma4, text a model quotes could be parsed as a second tool call. Fixed in v0.9.5.
An OpenShell gateway with no auth configured gave every caller admin rights. OpenShell v0.1.6, out 27 October, makes it refuse to start unless you opt in.
In Copilot CLI, the Copilot app and VS Code, a model reviews permission requests and auto-approves clearly safe ones. How to turn it on, and its limits.
Long prompts to GLM-5.3 on Workers AI could return text from other users' requests from 27 Aug to 9 Sep. Cloudflare and SGLang explain the bug and the fix.
Forever Security found an agent instructions file in a customer's Downloads folder. Its tests hijacked Codex and Claude Code. Never start an agent there.
The open-source Rust CAD app now writes an MCP entry into Claude, Cursor, Codex, VS Code and six more AI clients when it starts. One setting turns it off.