NVIDIA NemoClaw Flaw Lets Malicious Webpages Poison Local AI Models via Ollama
Oasis Security has disclosed a vulnerability in NVIDIA's NemoClaw, an open-source reference stack for running AI agents, that could allow an attacker-controlled…
Tag: Paperclip
Paperclip AI Flaws Let Attackers Run Host Commands via Malicious Agent Imports
Two critical vulnerabilities in Paperclip, an open-source control plane for AI agents, could allow attackers to execute arbitrary commands on a server…
GHSA-x8hx-rhr2-9rf7: DNS Rebinding in Paperclip Local Mode
A high-severity flaw in Paperclip's local_trusted mode allows DNS rebinding attacks to execute commands on the developer's machine with CVSS 9.6. Fixed…
GHSA-xfqj-r5qw-8g4j: Paperclip API Access Control Flaws
Multiple API routes in Paperclip lacked proper access checks, exposing sensitive data and control-plane details. Fixed in v2026.416.0 with added authentication and…
Paperclip: AI Model with Chat Template Poisoning Risk
Paperclip is an AI model that Oasis Security demonstrated could be poisoned via chat template manipulation, similar to the NemoClaw vulnerability. The…