CVE-2026-21852 is a vulnerability tracked across 4 threat clusters and 7 intelligence report mentions on ThreatCluster. First observed February 25, 2026; most recent activity May 26, 2026.
Claude Code, an agentic coding tool by Anthropic, has been found to have multiple vulnerabilities affecting various versions. CVE-2026-33068 allows attackers to bypass the trust dialog, enabling arbitrary tool execution…
Recent research highlights significant vulnerabilities in agentic AI systems, which can misclassify adversarial inputs as trusted instructions across six architectural layers. These vulnerabilities stem from trust…
AI coding assistants like Claude Code and GitHub Copilot are vulnerable to prompt injection attacks that exploit unvetted external artifacts. These attacks can turn coding assistants into attackers' shells, executing…
Anthropic has introduced Claude Code Security, a new feature designed to scan software codebases for vulnerabilities and suggest patching solutions. Initially available to a limited number of enterprise and team…