CVE-2026-41679

CVE-2026-41679 is a publicly disclosed software vulnerability assigned a unique identifier by the National Vulnerability Database. For AI governance teams, tracking such CVEs is critical because vulnerabilities in AI infrastructure, model serving platforms, or data processing systems can expose sensitive training data or enable unauthorized model manipulation. Organizations must integrate CVE monitoring into their AI risk management and vendor assessment processes to maintain security compliance and prevent exploits that could compromise model integrity or data privacy.

1 item

ResearchGlobal2026-08-05

Max-Severity Paperclip CVE Exposes Agent Trust Boundary Failures

Oasis Security disclosed three vulnerabilities in the open-source agentic AI platform Paperclip, including a max-severity authorization bypass tracked as CVE-2026-41679 that can be chained into remote code execution. The flaws also enable cross-tenant data exposure and developer-machine compromise through DNS rebinding. Patches are available in versions 2026.416.0 and 0.3.1.

agentic AI authorization vulnerabilities Paperclip Oasis Security CVE-2026-41679 open-source AI agent security least privilege