{"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-2025-54795 in the wild and no public exploit code.","fix":"Upgrade @anthropic-ai/claude-code to 1.0.20 or later.","what":"CVE-2025-54795 is a high-severity command injection vulnerability in anthropics claude-code, published on 5 Aug 2025. 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-2025-54795 and fix it if it is affected.\n\nWhat it is: CVE-2025-54795 is a high-severity command injection vulnerability in anthropics claude-code, published on 5 Aug 2025. 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-2025-54795 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 1.0.20\n- @anthropic-ai/claude-code (npm): affected all versions; fixed in 1.0.20\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-2025-54795/ (Markdown: https://insights.sbomify.com/CVE-2025-54795/index.md)","id":"CVE-2025-54795","markdown":"https://insights.sbomify.com/CVE-2025-54795/index.md","name":"CVE-2025-54795","record":{"aliases":["GHSA-x56v-x2h6-7j34"],"analysis":{"component_type":"developer_tool","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"Claude Code CLI","requires_auth":"none","summary":"Attackers can bypass approval prompts to execute arbitrary commands by injecting untrusted content into the context window.","user_interaction":"required","vuln_class":"command_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"claude_code","vendor":"anthropic"}],"cvss":{"score":8.7,"severity":"high","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-78","name":"Improper Neutralization of Special Elements used in an OS Command"}],"description":"Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This is fixed in version 1.0.20.","ecosystems":["npm"],"exploits":{"exploitdb":0,"first_seen":"2026-01-03","github_poc":1,"max_poc_stars":0,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-01-03T19:23:00Z","kind":"github_poc","ref":"https://github.com/alonisser/ralph","stars":0,"title":"Ralph Wiggum plugin implementation that works after the CVE-2025-54795 security patch"}],"tier":"poc_unverified"},"has_fix":true,"headline":"Claude Code echo command allowed bypass of user approval prompt for command execution","id":"CVE-2025-54795","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"npm","product":null,"products":[],"type":"command_injection","year":"2025"},"n_packages":2,"n_references":1,"next":{"headline":"Copyparty is vulnerable to Regex Denial of Service (ReDoS) attacks through \"Recent Uploads\" page","id":"CVE-2025-54796"},"packages":[{"ecosystem":"npm","fixed":["1.0.20"],"introduced":["0"],"last_affected":[],"package":"@anthropic-ai/claude-code","purl":null,"source":"GHSA-x56v-x2h6-7j34"},{"ecosystem":"npm","fixed":["1.0.20"],"introduced":["0"],"last_affected":[],"package":"@anthropic-ai/claude-code","purl":"pkg:npm/%40anthropic-ai/claude-code","source":"GHSA-x56v-x2h6-7j34"}],"prev":{"headline":"Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access","id":"CVE-2025-54794"},"products":["claude-code"],"published":"2025-08-05","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":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)"},{"class":"open","licence":"CC0","name":"PoC-in-GitHub"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2025-08-05","vendors":["anthropics"]},"summary":"Attackers can bypass approval prompts to execute arbitrary commands by injecting untrusted content into the context window.","url":"https://insights.sbomify.com/CVE-2025-54795/"}