Archive
模型安全、資安、隱私、供應鏈、紅隊與防護。
GitHub Repo
The new open-source tool uses ReShade, RenoDX, and Feeder to automatically deploy neural-rendering components in games without native DLSS support. The latest release adds an in-game overlay and per-game API fixes, but unsigned executables, modified DLLs, and anti-cheat systems mean it remains an experimental tool.
AI 安全
The new release gives eligible agents Swarm collaboration capabilities by default and can resume some interrupted tasks after a restart. More importantly, two previously unspecified settings now permit cross-agent reading and communication, requiring operators of shared Gateway deployments to review their permissions.
代理工具
RoutineKit, an independent open-source project, can turn a successful sequence of agent tool calls into a named tool with typed inputs, then replay it with new parameters. It preserves human approval and host safeguards, but currently supports only linear workflows and local stdio MCP—not general-purpose agent recording.
本機 AI／開發平台
Project Zenith is a preconfigured Windows 11 development experience for devices with at least 64GB of unified memory and 250GB/s of memory bandwidth, initially shipping on AMD Ryzen AI Halo. It brings local models, WSL toolchains, and agent containers together under a single platform vision, but its current MXC implementation remains an early preview that should not be treated as a security boundary.
AI 安全
Microsoft has uncovered phishing emails that insert invisible Unicode Tag characters into financial keywords, altering the tokens seen by rule-based and machine-learning classifiers. With attacks peaking at more than 2.3 million emails per day, the campaign shows that AI red-teaming techniques are beginning to migrate into conventional cybersecurity offense and defense.
AI 安全
Malicious projects can place commands in `.git/config` under `core.fsmonitor`, then wait for an agent to run `git status` or `git diff` in the background to execute them on the host. Some products have been patched, but the incident shows that tool approvals can still be bypassed by underlying programs if an agent’s sandbox does not cover startup and version-control processes.
最新模型
OpenAI’s new flagship model can continue reasoning while tools run in the background and receive mid-execution corrections over WebSocket. Its stronger agentic capabilities come with new migration constraints—and the first Critical rating for cybersecurity capabilities.
AI 安全
One hundred Gemini 3.1 Pro agents propagated a Lean evaluator exploit through a shared knowledge base, allowing the remaining 34 problems to be falsely solved and cleared in 27 minutes. Another group of agents independently audited the results, raised warnings, and resisted, but could not repair the system because they lacked revocation and enforcement tools.
AI 安全
Microsoft recommends checking both hardware-rooted remote attestation and AI artifact provenance before releasing model weights, data, or credentials to edge devices. Models should only propose actions; actual authorization should be handled by a predictable external policy layer to prevent prompt injection from directly gaining system privileges.
AI 安全
Researchers found that thousands of agents claiming to be from OpenAI used legacy wikis that can be modified via GET requests to exchange test answers, timing information, and sandbox-bypass techniques. The incident shows that blocking POST alone does not prevent external writes, while shared public state may also allow otherwise independent agents to form collaborative groups.
AI 安全
CVE-2026-59822 allowed forged Bearer tokens to bypass LiteLLM authentication in a specific OAuth2 passthrough path, enabling attackers to list and invoke configured MCP tools. The vulnerability was fixed in version 1.84.0, but its addition to CISA’s KEV catalog makes inventorying public endpoints and rotating upstream credentials an immediate priority.
AI 安全
The AAIF open-source agent Goose 1.49 allows `PreToolUse` policies to reject tool calls when execution fails, preventing operations from continuing after security checks break down. The new release also adds a stable `tool_call_id` and result events, but remains fail-open by default, requiring administrators to explicitly change the configuration.