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
The Hacker News AI Security · October 24, 2026

LiteLLM release compromise: revoke exposed keys and isolate publishing authority

news Agent SecurityAI Engineering
Why it matters

LiteLLM’s incident account traces its malicious 1.107.0 release to an exposed Agent Platform master key that was never revoked. The attacker obtained an organization-owner GitHub token, extracted more credentials through workflows and changed the release source. Stolen identities also satisfied approval steps. This account supersedes the maintainers’ earlier hypothesis about token leakage from logs.

My takeaway: Treat removal of a leaked secret from Git history as incomplete until revocation is verified. Inventory credentials reachable through agent platforms and CI; replace broad personal tokens with scoped workload identities. Audit release-source changes, protection overrides, temporary branches and deleted runs. Keep publishing approval and its credentials outside the same compromise path.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

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.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.

OWASP GenAI Security Project · tool

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.