AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
JFrog Security Research · October 7, 2026

LMCache advisory: restrict the multiprocess ZeroMQ listener

analysis AI EngineeringAgent Security
Why it matters

JFrog’s October 7 advisory describes CVE-2026-105192 in LMCache’s multiprocess transport: an unauthenticated message can reach Python pickle deserialization before request-handler checks and execute code with the service’s privileges. Remote exposure depends on making the ZeroMQ listener reachable; it binds to localhost by default, and in-process use does not expose this transport. The advisory lists versions from 0.3.9 through 0.5.5 and 0.5.6 release-candidate/development builds as affected, with no fixed release identified at publication.

My takeaway: Check the deployed mode, actual listener address and firewall rules before assigning exposure. Keep the port local or limited to trusted peers, reduce service privileges, and check the current upstream fix status. Network isolation limits reachability but does not repair unsafe deserialization.
Keep exploring

More curated notes connected through AI Engineering and Agent Security.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

Microsoft Security Blog · guide

AI vulnerability research: measure reproducible findings and completed fixes

Microsoft’s FORGE account describes the work between a model’s vulnerability claim and a useful repair: reusable builds, duplicate removal, reachability checks, project-specific verification, reproducible triggers and regression tests. Structured rejection reasons help improve later searches. The useful operational measure is the flow of findings that survive verification and reach a fix, rather than the number of candidates generated. Reported successful-case costs exclude parts of screening, failed attempts and human work, so they are not the total cost of operating this pipeline.

OpenAI News · framework

Frontier training safety cases: connect evidence to enforced pause and rollback controls

OpenAI proposes training-run safety cases combining alignment evaluations, containment and monitoring with explicit operational ownership. Concrete measures include immutable transcripts, held-out incident tests, checks for evaluation gaming, response deadlines and fail-closed monitoring. Independent internal challenge, leadership vetoes and tracking downstream uses support stopping a run and reversing affected work. The article describes recommendations still being implemented, rather than audited proof that every safeguard already operates or that residual risk has been eliminated.