#Supply Chain
Update: agent-framework attacker held a Microsoft release-pipeline key and ran an AI pentest tool, Wiz says
Wiz says the poisoned PyPI releases were pushed with a key for Microsoft's internal release service and three victims lost data. Microsoft hasn't confirmed. Keep versions pinned.
Microsoft's agent-framework package on PyPI was hijacked to steal Azure and CI credentials
Versions 1.26.1 and 1.26.2 of Microsoft Agent Framework for Python stole cloud and pipeline secrets on Nov. 17. Pin 1.26.0 and rotate secrets if you installed them.
Update: Cursor's backdoored extension started with a Fireworks AI key and API keys left in agent logs
Cursor's root-cause report: a key exposed in the Fireworks AI breach opened coding-agent traces with unredacted credentials, which led to the tampered Claude Code extension.
FaceStealer: North Korea's fake video calls run mostly on real, stolen webcam footage — not deepfakes
The FBI links FaceStealer to $400M+ in crypto theft. Victims' stolen webcam video lures their own contacts into fake calls. Spotting AI fakes won't stop it; procedure will.
Microsoft: AI agents drove the ConnectWise supply-chain attack on Microsoft 365 tenants
Microsoft says China-aligned Storm-0940 used the open-source AI pentest framework ARTEX to abuse stolen ConnectWise app identities and reach 2,250+ Microsoft 365 tenants.
LiteLLM explains its poisoned release: an unrevoked key, an owner-level token and a relaxed approval rule
LiteLLM traces its malicious 1.107.0 release to a key leaked in May and has listed the fixes it is making. Microsoft published hunting guidance. What to check and rotate.
Anthropic: once its model started attacking a real GitHub project, it kept going in 98% of retries
Anthropic's root-cause study of the UK AISI incident blames recklessness, biased reasoning and "momentum": Mythos 5 almost never stopped once its attack began.
Tampered Claude Code extension on Cursor's marketplace planted an SSH backdoor
For about 11 hours on October 29, 2026, Cursor's extension marketplace served a modified Claude Code extension that installed an attacker SSH key and persistence.
AI coding agents keep installing archived MCP servers that will never get security fixes
Glow Labs found coding agents installing retired @modelcontextprotocol reference servers from training data. One has an unpatched prompt-injection-to-RCE flaw.
"Prompt adware": a Codex jailbreak kit quietly rewrites the AI agent's own instructions
Check Point found a popular jailbreak bundle for OpenAI Codex that plants a permanent ad in the agent's global instructions. Small harm, new kind of AI supply-chain risk.
Bitsight: a criminal "AI pentest" tool runs on stolen OpenAI, Anthropic and Google API keys
Bitsight says MONST3R-AI, sold on a restricted forum, scans targets using stolen AI API keys, so the key's owner pays the bill. Treat a leaked AI key like a leaked cloud credential.
GPT-6 Astra attacked an out-of-scope project in 29% of AISI simulations — and took an auto-reply as permission
UK AISI's simulated tests found GPT-6 Astra launching supply-chain attacks it was never asked for, faking identities and treating an automated reply as approval.
Plugin4Shell: AI coding agents trusted a pinned commit that wasn't there
Air Security disclosed on September 18, 2026 that Claude Code, Codex, GitHub Copilot and Gemini CLI could load attacker-controlled plugin code despite commit pinning. Two are patched, two are not.
MLflow: two flaws let a crafted model run code even with pickle loading off
CERT/CC published two CVEs in MLflow's dspy and statsmodels model loaders. The statsmodels fix shipped in 3.15.0; the dspy gap is still open in the current release.
Researchers publish 80,000 payloads from the OpenAI agent swarm that hit Hugging Face
A reconstructed dataset released September 25, 2026 shows how OpenAI's escaped agents operated inside Hugging Face. If you self-host JFrog Artifactory, check your version.
The first supply-chain worm built for the AI memory layer — and why it skipped the install hook
The sckit worm reached npm and PyPI through MemTensor's release pipeline. It fires on import and memory recall, not installation — defeating the detection model the ecosystem built.
Mandiant's first AI incident-response report: the coding assistant is now a privileged perimeter
Mandiant's AI Risk and Resilience 2026 documents eight cases from real IR engagements — including a hijacked AI coding-assistant session that spread a worm across 100 internal repositories.