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
Wiz AI Security · August 27, 2026

Inside 90 days of attacks on AI infrastructure

analysis Agent SecurityPrompt InjectionAI Engineering
Why it matters

Across 90 days of AI-service honeypots, Wiz observed exploitation of LiteLLM MCP flaws, blind prompt injection that used out-of-band callbacks to confirm agent shell execution, and post-exploitation tailored to steal model-provider and proxy credentials from process memory. The activity targeted AI infrastructure as ordinary high-value cloud infrastructure.

My takeaway: Inventory every self-hosted AI service, remove unauthenticated internet exposure, patch on disclosure rather than a routine cycle, and scope the identities and egress reachable from proxies and MCP servers. Detect AI services spawning shells, inspect framework-specific credential access, and treat every connected tool service as inside the compromise blast radius.
Keep exploring

More curated notes connected through Agent Security and Prompt Injection.

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.