Archive
模型安全、資安、隱私、供應鏈、紅隊與防護。
GitHub Repo
A report on October 19 says smart approval may automatically allow AppleScript commands that close unsaved presentations, risking user data loss. Another contributor reproduced the approval gap. The community proposed a patch branch requiring human confirmation, but no official fix has been released.
GitHub Repo
Tenable disclosed a Hermes Agent native login vulnerability on October 9: differences in how the server and browser parse callback URLs could allow authorization codes to be sent to an attacker. The fix is included in v0.21.6, but the Desktop, Termux, and Microsoft Store packages were not updated alongside this release.
GitHub Repo
A PyTorch community report on October 9 says that a combination of certain short sequences and Boolean masks on B300 may cause NaNs during cuDNN attention backpropagation, even though forward outputs remain normal. Maintainers said the issue did not reproduce with newer cuDNN and recommended testing a nightly build or 2.15 release candidate; the reporter’s environment has yet to be upgraded and verified.
GitHub Repo
Nous Research released Hermes Agent v0.21.6 on October 8, fixing security issues involving dashboard login and configuration in untrusted repositories. The stable release includes Docker images and a Git tag; the desktop app and Termux package remain on their current versions.
GitHub Repo
LangGraph maintainers published a security advisory on October 7, reporting that the JS SDK modifies caller-provided header objects, which may cause clients to share credentials. The advisory lists patched versions, but the issue requires a specific shared-object configuration to trigger and is rated low risk.
最新模型
Mistral launched a public preview of Large 4 on October 6, featuring a native multimodal MoE architecture. Model weights are expected by the end of the month. An independent cybersecurity evaluation found strong vulnerability-handling performance, but passing the test does not mean the original vulnerability was fully fixed.
GitHub Repo
Non-admins with tool export permission could download the Python source code of tools shared with them as read-only. The issue was fixed in 0.11.4; operators should review group permissions and check whether credentials are embedded in code.
AI 安全
Validation covers central settings and team overrides, reporting the affected file and JSON path. Settings still need to sync to supported clients, and passing validation does not confirm they are effective.
AI 安全
A study tested log deletion, skill injection, and reward shaping in full-access mode, exposing risks when agent permissions overlap with audit data. The team published its experimental framework, but the results are limited by permission settings and the design of the human-defined rewards.
代理工具
When handling security alerts, the agent can consult existing memories and save newly generated fix patterns for other Copilot features to use. The feature remains in public preview, and GitHub has not published data on improvements to success rates or costs.
GitHub Repo
The release updates dependencies to address TLS certificate validation and process pool blocking risks. Unresolved vulnerabilities remain in the default images, with actual impact depending on execution paths.
AI 安全
The vulnerability involves the RPyC service on disaggregated prefill/decode nodes and requires an attacker to reach the control port. A public reproduction shows that health checks can still pass after exploitation; the advisory has yet to list a patched version.