# Anthropic vulnerabilities Source: https://junglewise.ai/threats/vendors/anthropic Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 13 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/vendors/anthropic.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 72 vulnerabilities in Anthropic: 0 in the last 7 days and 18 in the last 90 days, 4 of them critical and 0 exploited in the wild. The most recent, CVE-2026-111769, was published on 5 November 2026. 11 vulnerabilities in the last four weeks, up 120% on the four before (5). 1 critical against 0. 8 technologies have a page of their own. ## Counts - Last 7 days: 0 - Last 30 days: 11 - Last 90 days: 18 - All time: 72 (4 critical, 0 exploited in the wild) ## About Anthropic AI safety company that develops large language models and AI systems. ## Latest Anthropic vulnerabilities - [CVE-2026-111769: MCP TypeScript client SDK credential leak via cross-origin redirects](https://junglewise.ai/threats/cve-2026-111769-mcp-typescript-client-sdk-http-client-transports-and-oauth) (medium, CVSS 6.5, published 5 Nov 2026) - [CVE-2026-111768: MCP TypeScript SDK memory exhaustion via unbounded validation](https://junglewise.ai/threats/cve-2026-111768-mcp-typescript-sdk-one-http-request-within-the-default-size) (high, CVSS 7.5, published 5 Nov 2026) - [CVE-2026-111771: MCP TypeScript SDK bearer authentication token validation bypass](https://junglewise.ai/threats/cve-2026-111771-mcp-typescript-sdk-server-bearer-authentication-accepted-tokens) (medium, CVSS 6.8, published 5 Nov 2026) - [CVE-2026-88968: Anthropic Claude Code time-of-check-to-time-of-use in Edit tool](https://junglewise.ai/threats/cve-2026-88968-claude-code-is-an-agentic-coding-tool-prior-to-2-1-251-the-edit) (high, CVSS 4, published 3 Nov 2026) - [CVE-2026-88066: Anthropic Claude Desktop arbitrary code execution via uncontrolled search path](https://junglewise.ai/threats/cve-2026-88066-claude-desktop-is-anthropic-s-desktop-application-for-interacting) (info, published 3 Nov 2026) - [CVE-2026-116686: Model Context Protocol Python SDK unvalidated $ref fetching](https://junglewise.ai/threats/cve-2026-116686-the-model-context-protocol-python-sdk-is-the-official-python-sdk) (medium, CVSS 6.5, published 27 Oct 2026) - [CVE-2026-116685: Model Context Protocol Python SDK credential and body leak on cross-origin redirects](https://junglewise.ai/threats/cve-2026-116685-the-model-context-protocol-python-sdk-is-the-official-python-sdk) (medium, CVSS 5.9, published 27 Oct 2026) - [CVE-2026-116684: Model Context Protocol Python SDK token resource confusion in bearer authentication](https://junglewise.ai/threats/cve-2026-116684-the-model-context-protocol-python-sdk-is-the-official-python-sdk) (medium, CVSS 6.8, published 27 Oct 2026) - [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-2026-86063: Anthropic Claude Code plugin hash pin bypass in git checkout](https://junglewise.ai/threats/cve-2026-86063-claude-code-plugin-hash-pin-bypass-allows-bypass-of-hash-pinning) (high, CVSS 4, published 15 Oct 2026) - [CVE-2026-59951: MCP Python SDK unbounded session accumulation in StreamableHTTP](https://junglewise.ai/threats/cve-2026-59951-mcp-python-sdk-unbounded-session-accumulation-in-streamablehttp) (high, CVSS 7.5, published 14 Oct 2026) - [CVE-2026-108714: MCP Kotlin SDK uncontrolled memory allocation in WebSocket](https://junglewise.ai/threats/cve-2026-108714-mcp-kotlin-sdk-through-0-15-0-contains-an-uncontrolled-memory) (high, CVSS 7.5, published 11 Oct 2026) - [CVE-2026-104850: MCP TypeScript SDK OAuth client credential injection via untrusted server](https://junglewise.ai/threats/cve-2026-104850-mcp-typescript-sdk-oauth-client-could-send-credentials-to-an) (high, CVSS 7.5, published 6 Oct 2026) - [CVE-2026-103012: Anthropic Claude Code managed settings bypass with stored API key](https://junglewise.ai/threats/cve-2026-103012-claude-code-selected-an-api-key-stored-by-claude-code-for) (info, published 30 Sep 2026) - [CVE-2026-63128: RMCP Streamable HTTP server unauthenticated session-table memory leak](https://junglewise.ai/threats/cve-2026-63128-rmcp-streamable-http-server-unauthenticated-session-table-memory) (high, CVSS 7.5, published 16 Sep 2026) - [CVE-2026-63127: RMCP missing resource field validation in OAuth metadata](https://junglewise.ai/threats/cve-2026-63127-rmcp-missing-resource-field-validation-in-oauth-metadata) (high, CVSS 8.2, published 16 Sep 2026) - [CVE-2026-84810: Anthropic claude-skill-antivirus incomplete file analysis in skill scanning](https://junglewise.ai/threats/cve-2026-84810-anthropic-claude-skill-antivirus-incomplete-file-analysis-in) (medium, CVSS 6.5, published 2 Sep 2026) - [CVE-2026-53965: MCP PHP SDK unbounded SSE buffer memory exhaustion](https://junglewise.ai/threats/cve-2026-53965-mcp-php-sdk-unbounded-sse-buffer-memory-exhaustion) (high, CVSS 4, published 25 Aug 2026) - [CVE-2026-67432: Model Context Protocol Ruby SDK memory exhaustion in StreamableHTTPTransport](https://junglewise.ai/threats/cve-2026-67432-model-context-protocol-ruby-sdk-memory-exhaustion-in) (high, CVSS 7.5, published 29 Jul 2026) - [CVE-2026-55407: Anthropics Buffa memory exhaustion in protobuf decoder](https://junglewise.ai/threats/cve-2026-55407-anthropics-buffa-memory-exhaustion-in-protobuf-decoder) (medium, CVSS 4, published 16 Jul 2026) - [CVE-2026-55406: Anthropics Buffa use-after-free in OwnedView](https://junglewise.ai/threats/cve-2026-55406-anthropics-buffa-use-after-free-in-ownedview) (medium, CVSS 4, published 16 Jul 2026) - [CVE-2026-47751: Anthropic Claude Code Action arbitrary code execution in GitHub Actions runner](https://junglewise.ai/threats/cve-2026-47751-anthropic-claude-code-action-arbitrary-code-execution-in-github) (medium, CVSS 5.3, published 16 Jul 2026) - [CVE-2026-59950: modelcontextprotocol python-sdk missing origin validation in WebSocket transport](https://junglewise.ai/threats/cve-2026-59950-modelcontextprotocol-python-sdk-missing-origin-validation-in) (high, CVSS 4, published 15 Jul 2026) - [CVE-2026-52870: Model Context Protocol Python SDK missing authorization in experimental tasks](https://junglewise.ai/threats/cve-2026-52870-model-context-protocol-python-sdk-missing-authorization-in) (high, CVSS 7.6, published 15 Jul 2026) - [CVE-2026-52869: modelcontextprotocol mcp authorization bypass in SSE and HTTP transports](https://junglewise.ai/threats/cve-2026-52869-modelcontextprotocol-mcp-authorization-bypass-in-sse-and-http) (high, CVSS 7.1, published 15 Jul 2026) ## Most severe Anthropic vulnerabilities - [CVE-2026-39861: Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace](https://junglewise.ai/threats/cve-2026-39861-claude-code-sandbox-escape-via-symlink-following-allows-arbitrary) (critical, CVSS 10, published 21 Apr 2026) - [CVE-2025-64755: Anthropic claude-code sed command validation bypass](https://junglewise.ai/threats/cve-2025-64755-anthropic-claude-code-sed-command-validation-bypass) (critical, CVSS 9.8, published 21 Nov 2025) - [CVE-2025-65099: Anthropic Claude Code command execution prior to trust dialog](https://junglewise.ai/threats/cve-2025-65099-anthropic-claude-code-command-execution-prior-to-trust-dialog) (critical, CVSS 9.8, published 19 Nov 2025) - [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-2026-40068: Anthropic Claude Code trust bypass via Git worktree spoofing](https://junglewise.ai/threats/cve-2026-40068-anthropic-claude-code-trust-bypass-via-git-worktree-spoofing) (high, CVSS 8.8, published 5 May 2026) - [CVE-2026-42559: Model Context Protocol RMCP DNS rebinding in Streamable HTTP server](https://junglewise.ai/threats/cve-2026-42559-model-context-protocol-rmcp-dns-rebinding-in-streamable-http) (high, CVSS 8.8, published 14 May 2026) - [CVE-2026-7574: Anthropic Claude Desktop Cowork missing integrity check in VM image handling](https://junglewise.ai/threats/cve-2026-7574-anthropic-claude-desktop-cowork-missing-integrity-check-in-vm) (high, CVSS 8.7, published 24 Jun 2026) - [CVE-2026-63127: RMCP missing resource field validation in OAuth metadata](https://junglewise.ai/threats/cve-2026-63127-rmcp-missing-resource-field-validation-in-oauth-metadata) (high, CVSS 8.2, published 16 Sep 2026) - [CVE-2025-66416: Model Context Protocol Python SDK DNS rebinding in HTTP servers](https://junglewise.ai/threats/cve-2025-66416-model-context-protocol-python-sdk-dns-rebinding-in-http-servers) (high, CVSS 8.1, published 2 Dec 2025) - [CVE-2026-22561: Anthropic Claude for Windows privilege escalation in installer](https://junglewise.ai/threats/cve-2026-22561-anthropic-claude-for-windows-privilege-escalation-in-installer) (high, CVSS 7.8, published 31 Mar 2026) ## Vulnerabilities per week 11 vulnerabilities in the last four weeks, up 120% on the four before (5). 1 critical against 0. | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 1 | 0 | 0 | | 31 Aug 2026 | 1 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 2 | 0 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 1 | 0 | 0 | | 5 Oct 2026 | 2 | 0 | 0 | | 12 Oct 2026 | 3 | 1 | 0 | | 19 Oct 2026 | 0 | 0 | 0 | | 26 Oct 2026 | 3 | 0 | 0 | | 2 Nov 2026 | 5 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## 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 Claude Agent SDK](https://junglewise.ai/threats/technologies/claude-agent-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 vulnerabilities", https://junglewise.ai/threats/vendors/anthropic, 13 November 2026.