5 incidents

Risk: Supply-chain compromise Control: Provenance checks on retrieval and training data Outcome: Not stated in sources

EffectiveNot effectiveNot effective (bypassed)Did not existNot stated in sourcesNot yet checkedAttacker's ownOrder: model · harness · application · target

Date	Incident	Risk	Controls mentioned in sources
2026-10-30	Backdoored Anthropic Claude VS Code extension on Cursor marketplace (v2.1.313) installs SSH backdoor for up to 5,000 developers Anthropic	Supply-chain compromise	EffectiveStop control L2 Did not existVetting of plug-ins, skills and dependencies L3
2026-06-01	OpenAI Codex authentication tokens stolen via malicious npm package codexui-android OpenAI	Supply-chain compromise	Did not existEncryption of stored data L3
2026-02-02	341 malicious ClawHub skills found stealing data from OpenClaw users	Supply-chain compromise	Did not existVetting of plug-ins, skills and dependencies L3
2026-02-01	ClawHavoc: 341 malicious skills on OpenClaw's ClawHub deliver infostealers Peter Steinberger	Supply-chain compromise	Did not existVetting of plug-ins, skills and dependencies L3
2025-08-26	Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltration	Supply-chain compromise	Did not existLeast-privilege access for the agent L3 EffectiveSafety training and refusal L1