# Anthropic Claude Agent SDK vulnerabilities Source: https://junglewise.ai/threats/technologies/claude-agent-sdk Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 9 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/technologies/claude-agent-sdk.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 4 vulnerabilities in Anthropic Claude Agent SDK: 0 in the last 7 days and 1 in the last 90 days, 1 of them critical and 0 exploited in the wild. The most recent, CVE-2026-96620, was published on 16 October 2026. 1 vulnerability in the last four weeks, up from none in the four before. 1 critical against 0. ## Counts - Last 7 days: 0 - Last 30 days: 1 - Last 90 days: 1 - All time: 4 (1 critical, 0 exploited in the wild) ## About Anthropic Claude Agent SDK The Claude Agent SDK is a software development kit for building autonomous agents and integrating Claude AI models into applications. ## Latest Anthropic Claude Agent SDK vulnerabilities - [CVE-2026-96620: Claude Agent SDK argument injection via resume option](https://junglewise.ai/threats/cve-2026-96620-claude-agent-sdk-argument-injection-via-resume-option-allows) (critical, CVSS 4, published 16 Oct 2026) - [CVE-2026-35022: Anthropic Claude Code OS command injection in authentication helpers](https://junglewise.ai/threats/cve-2026-35022-anthropic-claude-code-os-command-injection-in-authentication) (info, CVSS 9.8, published 6 Apr 2026) - [CVE-2026-35021: Anthropic Claude Code OS command injection in prompt editor](https://junglewise.ai/threats/cve-2026-35021-anthropic-claude-code-os-command-injection-in-prompt-editor) (info, CVSS 7.8, published 6 Apr 2026) - [CVE-2026-35020: Anthropic Claude Code CLI OS command injection in command lookup helper](https://junglewise.ai/threats/cve-2026-35020-anthropic-claude-code-cli-os-command-injection-in-command-lookup) (info, CVSS 8.4, published 6 Apr 2026) ## Most severe Anthropic Claude Agent SDK vulnerabilities - [CVE-2026-96620: Claude Agent SDK argument injection via resume option](https://junglewise.ai/threats/cve-2026-96620-claude-agent-sdk-argument-injection-via-resume-option-allows) (critical, CVSS 4, published 16 Oct 2026) - [CVE-2026-35022: Anthropic Claude Code OS command injection in authentication helpers](https://junglewise.ai/threats/cve-2026-35022-anthropic-claude-code-os-command-injection-in-authentication) (info, CVSS 9.8, published 6 Apr 2026) - [CVE-2026-35020: Anthropic Claude Code CLI OS command injection in command lookup helper](https://junglewise.ai/threats/cve-2026-35020-anthropic-claude-code-cli-os-command-injection-in-command-lookup) (info, CVSS 8.4, published 6 Apr 2026) - [CVE-2026-35021: Anthropic Claude Code OS command injection in prompt editor](https://junglewise.ai/threats/cve-2026-35021-anthropic-claude-code-os-command-injection-in-prompt-editor) (info, CVSS 7.8, published 6 Apr 2026) ## Vulnerabilities per week 1 vulnerability in the last four weeks, up from none in the four before. 1 critical against 0. | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 0 | 0 | 0 | | 31 Aug 2026 | 0 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 0 | 0 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 0 | 0 | 0 | | 5 Oct 2026 | 0 | 0 | 0 | | 12 Oct 2026 | 1 | 1 | 0 | | 19 Oct 2026 | 0 | 0 | 0 | | 26 Oct 2026 | 0 | 0 | 0 | | 2 Nov 2026 | 0 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## Other Anthropic technologies - [Anthropic Claude Code](https://junglewise.ai/threats/technologies/claude-code): 31 vulnerabilities - [Anthropic Model Context Protocol](https://junglewise.ai/threats/technologies/model-context-protocol): 11 vulnerabilities - [Anthropic Claude Desktop](https://junglewise.ai/threats/technologies/claude-desktop): 6 vulnerabilities - [Anthropic Model Context Protocol SDK (TypeScript)](https://junglewise.ai/threats/technologies/model-context-protocol-sdk-typescript): 5 vulnerabilities - [Anthropic @Modelcontextprotocol/Sdk](https://junglewise.ai/threats/technologies/anthropic-modelcontextprotocol-sdk): 4 vulnerabilities - [Anthropic Model Context Protocol Python SDK](https://junglewise.ai/threats/technologies/anthropic-model-context-protocol-python-sdk): 3 vulnerabilities - [Anthropic Claude Code CLI](https://junglewise.ai/threats/technologies/claude-code-cli): 3 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "Anthropic Claude Agent SDK vulnerabilities", https://junglewise.ai/threats/technologies/claude-agent-sdk, 9 November 2026.