Debates
0day Rubbish publishes seven AI-assisted findings and puts direct disclosure first
Community reports 2 sources
0
0day Rubbish
Project Oct 20, 2026
A community vulnerability-research project that attributes discovery to a multi-model AI pipeline and publishes technical advisories and exploit demonstrations in recurring batches.
Visit primary link
2 sources attached
What happened lately
0day Rubbish timeline
0day Rubbish describes an AI-assisted vulnerability-research pipeline using Claude, OpenAI, DeepSeek, GLM and Kimi, followed by manual validation. Its stated approach favors recurring public disclosure of technical findings and proof-of-concept code as pressure for vendors to improve security. Listing model providers does not establish that those companies endorse the project or its disclosure policy.
The repository is MIT-licensed. Its October 19 Batch 15 release lists seven advisory claims concerning six commercial products. The detailed README distinguishes live-product testing from controlled replicas, supplied deployment conditions and static inference. These are the researchers’ findings and verification descriptions, not an independent AITrending reproduction or confirmation that every affected version remains unpatched.