UTC

Claude Code

By Anthropic. 34 published vulnerabilities.

Advisories
34
Critical
0
Exploited in the wild
None listed
Latest
2026-11-09
Vulnerabilities
SeverityVulnerabilityPublishedFixed in
HighClaude Code: TOCTOU Race in Edit Tool Allows File Writes Outside the WorkspaceCVE-2026-88968 · GHSA-5xjx-9qx6-jcrv2026-11-092.1.251
HighClaude Code: Plugin Hash Pin Bypass Allows Bypass of Hash PinningCVE-2026-86063 · GHSA-pq7j-f95f-qfcv2026-10-152.1.179
HighUncontrolled Search Path Enables Arbitrary Code Execution via Malicious Git ExecutableCVE-2026-88066 · GHSA-4p2j-qj3c-6x842026-10-13See advisory
HighArbitrary File Write via Write-Time Symlink Following (TOCTOU) in Claude CodeCVE-2026-103435 · GHSA-5j29-h97v-84ch2026-10-05See advisory
LowManaged Settings Not Applied When a Stored API Key Was Preferred Over Enterprise Sign-InCVE-2026-103012 · GHSA-gfvf-j8jh-jxxw2026-09-29See advisory
HighClaude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code ExecutionCVE-2026-55607 · GHSA-7835-87q9-rgvv2026-07-242.1.163
Medium@anthropic-ai/claude-code has an Insecure Temporary File in /copy Command that Enables Response Disclosure and Symlink-Based File WriteCVE-2026-46406 · GHSA-4vp2-6q8c-pvq22026-06-252.1.128
MediumClaude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetchCVE-2026-54316 · GHSA-fg94-h982-f3mm2026-06-172.1.163
HighSSH Host Key Verification Bypass Allows Man-in-the-Middle Attack on Remote SessionsCVE-2026-44467 · GHSA-3rwf-2g6p-c2f92026-05-06See advisory
HighClaude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code ExecutionCVE-2026-40068 · GHSA-q5hj-mxqh-vv772026-04-242.1.84
HighClaude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside WorkspaceCVE-2026-39861 · GHSA-vp62-r36r-9xqp2026-04-212.1.64
MediumClaude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on WindowsCVE-2026-35603 · GHSA-5cwg-9f6j-9jvx2026-04-172.1.75
HighClaude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings FileCVE-2026-33068 · GHSA-mmgp-wc2j-qcv72026-03-192.1.53
LowClaude Code has Permission Deny Bypass Through Symbolic LinksCVE-2026-25724 · GHSA-4q92-rfm6-2cqx2026-02-062.1.7
HighClaude Code Vulnerable to Command Injection via Directory Change Bypasses Write ProtectionCVE-2026-25722 · GHSA-66q4-vfjg-2qhh2026-02-062.0.57
HighClaude Code has Sandbox Escape via Persistent Configuration Injection in settings.jsonCVE-2026-25725 · GHSA-ff64-7w26-62rf2026-02-062.1.2
HighClaude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write RestrictionsCVE-2026-25723 · GHSA-mhg7-666j-cqg42026-02-062.0.55
HighClaude Code has a Path Restriction Bypass via ZSH Clobber which Allows Arbitrary File WritesCVE-2026-24053 · GHSA-q728-gf8j-w49r2026-02-032.0.74
HighClaude Code has a Command Injection in find Command Bypasses User Approval PromptCVE-2026-24887 · GHSA-qgqw-h4xq-7w8w2026-02-032.0.72
HighClaude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled DomainsCVE-2026-24052 · GHSA-vhw5-3g5m-8ggf2026-02-031.0.111
MediumClaude Code Leaks Data via Malicious Environment Configuration Before Trust ConfirmationCVE-2026-21852 · GHSA-jh7p-qr78-84p72026-01-212.0.65
HighClaude Code Command Validation Bypass Allows Arbitrary Code ExecutionCVE-2025-66032 · GHSA-xq4m-mc3c-vvg32025-12-031.0.93
High@anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File WritesCVE-2025-64755 · GHSA-7mv8-j34q-vp7q2025-11-202.0.31
HighClaude Code vulnerable to command execution prior to startup trust dialogCVE-2025-65099 · GHSA-5hhx-v7f6-x7gv2025-11-191.0.39
HighClaude Code can execute commands prior to the startup trust dialogCVE-2025-59536 · GHSA-4fgq-fpq9-mr3g2025-10-031.0.111
LowClaude Code permission deny bypass through symlinkCVE-2025-59829 · GHSA-66m2-gx93-v9962025-10-031.0.120
HighClaude Code Vulnerable to Arbitrary Code Execution via Plugin Autoloading with Specific Yarn VersionsCVE-2025-59828 · GHSA-2jjv-qf24-vfm42025-09-241.0.39
HighClaude Code vulnerable to arbitrary code execution caused by maliciously configured git emailCVE-2025-59041 · GHSA-j4h9-wv2m-wrf72025-09-101.0.105
HighClaude Code rg vulnerability does not protect against approval prompt bypassCVE-2025-58764 · GHSA-qxfv-fcpc-w36x2025-09-101.0.105
HighClaude Code Vulnerable to Arbitrary Code Execution Due to Insufficient Startup WarningGHSA-ph6w-f82w-28w62025-09-031.0.87
HighClaude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude CodeCVE-2025-55284 · GHSA-x5gv-jw7f-j6xj2025-08-181.0.4
HighClaude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file accessCVE-2025-54794 · GHSA-pmw4-pwvc-3hx22025-08-040.2.111
HighClaude Code echo command allowed bypass of user approval prompt for command executionCVE-2025-54795 · GHSA-x56v-x2h6-7j342025-08-041.0.20
HighClaude Code Improper Authorization via websocket connections from arbitrary originsCVE-2025-52882 · GHSA-9f65-56v6-gxw72025-06-231.0.24

CVEs matched by the NVD's product names and advisories published in the product's own repository, checked 2026-11-22. Where the vendor runs the service, its fix reaches you without an update.

In MITRE ATLAS case studies

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].

This product uses the NVD API but is not endorsed or certified by the NVD. Product facts from github.com, checked 2026-11-18. Logos are their owners' marks, shown only to identify the products.