{"answers":{"affected":"2 open source packages ship an affected version, including @anthropic-ai/claude-code. It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-33068 in the wild and no public exploit code.","fix":"Upgrade @anthropic-ai/claude-code to 2.1.53 or later.","what":"CVE-2026-33068 is a high-severity vulnerability in anthropics claude-code, published on 20 Mar 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link."},"fix_prompt":"Check this codebase for CVE-2026-33068 and fix it if it is affected.\n\nWhat it is: CVE-2026-33068 is a high-severity vulnerability in anthropics claude-code, published on 20 Mar 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.\nExploitation: There is no known exploitation of CVE-2026-33068 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- @anthropic-ai/claude-code (npm): affected all versions; fixed in 2.1.53\n- @anthropic-ai/claude-code (npm): affected all versions; fixed in 2.1.53\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-33068/ (Markdown: https://insights.sbomify.com/CVE-2026-33068/index.md)","id":"CVE-2026-33068","markdown":"https://insights.sbomify.com/CVE-2026-33068/index.md","name":"CVE-2026-33068","record":{"aliases":["GHSA-mmgp-wc2j-qcv7"],"analysis":{"component_type":"developer_tool","fix_type":"patch","impacts":["code_execution","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"AI coding assistant","requires_auth":"none","summary":"Attackers can bypass workspace trust dialogs in Claude Code via malicious repository settings, enabling unauthorized tool execution without user consent.","user_interaction":"required","vuln_class":"security_feature_bypass"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"claude_code","vendor":"anthropic"}],"cvss":{"score":7.7,"severity":"high","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-807","name":"Reliance on Untrusted Inputs in a Security Decision"}],"description":"Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue has been patched in version 2.1.53.","ecosystems":["npm"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":true,"headline":"Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File","id":"CVE-2026-33068","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"npm","product":null,"products":[],"type":"security_feature_bypass","year":"2026"},"n_packages":2,"n_references":1,"next":{"headline":"PJSIP has an Out-of-bounds Read in SIP multipart parsing","id":"CVE-2026-33069"},"packages":[{"ecosystem":"npm","fixed":["2.1.53"],"introduced":["0"],"last_affected":[],"package":"@anthropic-ai/claude-code","purl":null,"source":"GHSA-mmgp-wc2j-qcv7"},{"ecosystem":"npm","fixed":["2.1.53"],"introduced":["0"],"last_affected":[],"package":"@anthropic-ai/claude-code","purl":"pkg:npm/%40anthropic-ai/claude-code","source":"GHSA-mmgp-wc2j-qcv7"}],"prev":{"headline":"SiYuan has Stored XSS to RCE via Unsanitized Bazaar Package Metadata","id":"CVE-2026-33067"},"products":["claude-code"],"published":"2026-03-20","related":[{"cvss_score":8.7,"headline":"Claude Code Command Validation Bypass Allows Arbitrary Code Execution","id":"CVE-2025-66032","kev_date_added":null,"published":"2025-12-03"},{"cvss_score":8.7,"headline":"@anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes","id":"CVE-2025-64755","kev_date_added":null,"published":"2025-11-21"},{"cvss_score":8.7,"headline":"Claude Code's startup trust dialog could lead to Command Execution attack","id":"CVE-2025-59536","kev_date_added":null,"published":"2025-10-03"},{"cvss_score":8.7,"headline":"Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution","id":"CVE-2025-58764","kev_date_added":null,"published":"2025-09-10"},{"cvss_score":8.7,"headline":"Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email","id":"CVE-2025-59041","kev_date_added":null,"published":"2025-09-10"},{"cvss_score":8.7,"headline":"Claude Code echo command allowed bypass of user approval prompt for command execution","id":"CVE-2025-54795","kev_date_added":null,"published":"2025-08-05"},{"cvss_score":7.7,"headline":"Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution","id":"CVE-2026-55607","kev_date_added":null,"published":"2026-06-29"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-03-20","vendors":["anthropics"]},"summary":"Attackers can bypass workspace trust dialogs in Claude Code via malicious repository settings, enabling unauthorized tool execution without user consent.","url":"https://insights.sbomify.com/CVE-2026-33068/"}