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 · October 21, 2026

LiteLLM compromise: inspect runtime artifacts and rebuild exposed environments

analysis Agent SecurityAI Red TeamingAI Engineering
Why it matters

Wiz and LiteLLM report malicious 1.107.0 wheels and container images containing Python startup hooks that steal credentials and load further code. The source release tag lacked the malicious files. LiteLLM says stolen GitHub credentials let the attacker alter the release workflow; the suspected route through gateway logs remains under investigation. A valid signature did not establish a trusted source.

My takeaway: Inventory installed wheels and executed image digests against the maintainer advisory. Avoid starting Python or pip in a suspect environment, since startup hooks can run again. Isolate and preserve evidence, rebuild from verified artifacts, and rotate credentials the environment could reach. Audit release-workflow changes, privileged approvals, and gateway logs for exposed tokens.
Keep exploring

More curated notes connected through Agent Security and AI Red Teaming.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

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.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.