Vendor
Anthropic vulnerabilities
Updated . Rebuilt every hour.
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.
- Last 7 days
- 0
- Last 90 days
- 18
- Critical, all time
- 4
- Exploited in the wild
- 0
About Anthropic
AI safety company that develops large language models and AI systems.
Anthropic technologies
Latest Anthropic vulnerabilities
- CVE-2026-111769: MCP TypeScript client SDK credential leak via cross-origin redirectsmediumCVSS 6.5
- CVE-2026-111768: MCP TypeScript SDK memory exhaustion via unbounded validationhighCVSS 7.5
- CVE-2026-111771: MCP TypeScript SDK bearer authentication token validation bypassmediumCVSS 6.8
- CVE-2026-88968: Anthropic Claude Code time-of-check-to-time-of-use in Edit toolhighCVSS 4EPSS 0.3%
- CVE-2026-88066: Anthropic Claude Desktop arbitrary code execution via uncontrolled search pathinfo
- CVE-2026-116686: Model Context Protocol Python SDK unvalidated $ref fetchingmediumCVSS 6.5EPSS 0.3%
- CVE-2026-116685: Model Context Protocol Python SDK credential and body leak on cross-origin redirectsmediumCVSS 5.9EPSS 0.4%
- CVE-2026-116684: Model Context Protocol Python SDK token resource confusion in bearer authenticationmediumCVSS 6.8EPSS 0.4%
- CVE-2026-96620: Claude Agent SDK argument injection via resume optioncriticalCVSS 4
- CVE-2026-86063: Anthropic Claude Code plugin hash pin bypass in git checkouthighCVSS 4EPSS 0.2%
- CVE-2026-59951: MCP Python SDK unbounded session accumulation in StreamableHTTPhighCVSS 7.5EPSS 0.5%
- CVE-2026-108714: MCP Kotlin SDK uncontrolled memory allocation in WebSockethighCVSS 7.5EPSS 0.4%
- CVE-2026-104850: MCP TypeScript SDK OAuth client credential injection via untrusted serverhighCVSS 7.5
- CVE-2026-103012: Anthropic Claude Code managed settings bypass with stored API keyinfo
- CVE-2026-63128: RMCP Streamable HTTP server unauthenticated session-table memory leakhighCVSS 7.5EPSS 0.6%
- CVE-2026-63127: RMCP missing resource field validation in OAuth metadatahighCVSS 8.2EPSS 0.2%
- CVE-2026-84810: Anthropic claude-skill-antivirus incomplete file analysis in skill scanningmediumCVSS 6.5EPSS 0.3%
- CVE-2026-53965: MCP PHP SDK unbounded SSE buffer memory exhaustionhighCVSS 4EPSS 0.6%
- CVE-2026-67432: Model Context Protocol Ruby SDK memory exhaustion in StreamableHTTPTransporthighCVSS 7.5EPSS 0.8%
- CVE-2026-55407: Anthropics Buffa memory exhaustion in protobuf decodermediumCVSS 4EPSS 0.8%
- CVE-2026-55406: Anthropics Buffa use-after-free in OwnedViewmediumCVSS 4EPSS 0.2%
- CVE-2026-47751: Anthropic Claude Code Action arbitrary code execution in GitHub Actions runnermediumCVSS 5.3
- CVE-2026-59950: modelcontextprotocol python-sdk missing origin validation in WebSocket transporthighCVSS 4EPSS 0.2%
- CVE-2026-52870: Model Context Protocol Python SDK missing authorization in experimental taskshighCVSS 7.6EPSS 0.4%
- CVE-2026-52869: modelcontextprotocol mcp authorization bypass in SSE and HTTP transportshighCVSS 7.1EPSS 0.5%
Most severe Anthropic vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-39861: Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside WorkspacecriticalCVSS 10EPSS 0.7%
- CVE-2025-64755: Anthropic claude-code sed command validation bypasscriticalCVSS 9.8EPSS 0.5%
- CVE-2025-65099: Anthropic Claude Code command execution prior to trust dialogcriticalCVSS 9.8EPSS 0.5%
- CVE-2026-96620: Claude Agent SDK argument injection via resume optioncriticalCVSS 4
- CVE-2026-40068: Anthropic Claude Code trust bypass via Git worktree spoofinghighCVSS 8.8EPSS 0.6%
- CVE-2026-42559: Model Context Protocol RMCP DNS rebinding in Streamable HTTP serverhighCVSS 8.8EPSS 0.2%
- CVE-2026-7574: Anthropic Claude Desktop Cowork missing integrity check in VM image handlinghighCVSS 8.7
- CVE-2026-63127: RMCP missing resource field validation in OAuth metadatahighCVSS 8.2EPSS 0.2%
- CVE-2025-66416: Model Context Protocol Python SDK DNS rebinding in HTTP servershighCVSS 8.1EPSS 0.5%
- CVE-2026-22561: Anthropic Claude for Windows privilege escalation in installerhighCVSS 7.8EPSS 0.2%
Vulnerabilities per week
11 vulnerabilities in the last four weeks, up 120% on the four before (5). 1 critical against 0. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 1 | 0 | |
| 31 Aug 2026 | 1 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 2 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 1 | 0 | |
| 5 Oct 2026 | 2 | 0 | |
| 12 Oct 2026 | 3 | 1 | |
| 19 Oct 2026 | 0 | 0 | |
| 26 Oct 2026 | 3 | 0 | |
| 2 Nov 2026 | 5 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Anthropic vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/vendors/anthropic)<a href="https://junglewise.ai/threats/vendors/anthropic"><img src="https://junglewise.ai/threats/vendors/anthropic/badge.svg" alt="Anthropic vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/vendors/anthropic.json, and this page as text at https://junglewise.ai/threats/vendors/anthropic.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Anthropic vulnerabilities", https://junglewise.ai/threats/vendors/anthropic, 13 November 2026.