{"answers":{"affected":"It affects 1 product.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-32625 exists.","fix":"No fix has been published for CVE-2026-32625 yet. Limit exposure of the affected software until one is available.","what":"CVE-2026-32625 is a critical vulnerability in Librechat Librechat, published on 2 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-32625 and fix it if it is affected.\n\nWhat it is: CVE-2026-32625 is a critical vulnerability in Librechat Librechat, published on 2 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-32625 exists.\n\nAffected product: Librechat Librechat. No package-level version data is available, so check the vendor advisory linked from the reference page.\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-2026-32625/ (Markdown: https://insights.sbomify.com/CVE-2026-32625/index.md)","id":"CVE-2026-32625","markdown":"https://insights.sbomify.com/CVE-2026-32625/index.md","name":"CVE-2026-32625","record":{"aliases":["GHSA-4pcc-j6m6-wcwx"],"analysis":{"component_type":"web_application","fix_type":"upgrade","impacts":["data_read","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"AI chat application","requires_auth":"low_privilege","summary":"Authenticated users can exfiltrate server secrets like JWT keys and database credentials by injecting environment variable references into MCP server URLs.","user_interaction":"not_required","vuln_class":"information_disclosure"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"librechat","vendor":"librechat"}],"cvss":{"score":9.6,"severity":"critical","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N","version":"3.1"},"cwes":[{"id":"CWE-200","name":"Exposure of Sensitive Information to an Unauthorized Actor"}],"description":"LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":false,"headline":"LibreChat Exfiltrates Server Secrets via MCP Server URL Injection","id":"CVE-2026-32625","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":"librechat:librechat","products":["librechat:librechat"],"type":"information_disclosure","year":"2026"},"n_packages":0,"n_references":1,"next":{"headline":"AnythingLLM has a Streaming Phase XSS to RCE via LLM Response Injection","id":"CVE-2026-32626"},"packages":[],"prev":{"headline":"xrdp: Heap buffer overflow in xrdp_sec_process_logon_info() via incorrect g_strncat length calculation","id":"CVE-2026-32624"},"products":["LibreChat"],"published":"2026-06-02","related":[{"cvss_score":9.4,"headline":"Improper Access Control in danny-avila/librechat","id":"CVE-2024-11167","kev_date_added":null,"published":"2025-03-20"},{"cvss_score":9.1,"headline":"LibreChat MCP Stdio Remote Command Execution","id":"CVE-2026-22252","kev_date_added":null,"published":"2026-01-12"},{"cvss_score":9.1,"headline":"LibreChat is vulnerable to Server-Side Request Forgery due to missing restrictions","id":"CVE-2025-69222","kev_date_added":null,"published":"2026-01-07"},{"cvss_score":9.1,"headline":"Path traversal in n/a","id":"CVE-2024-41704","kev_date_added":null,"published":"2024-07-22"},{"cvss_score":8.8,"headline":"Path Traversal in danny-avila/librechat","id":"CVE-2024-11170","kev_date_added":null,"published":"2025-03-20"},{"cvss_score":8.6,"headline":"LibreChat JSON Injection in Chat POST Allows Remote Resource Inclusion and PXSS via Image Upload","id":"CVE-2025-66450","kev_date_added":null,"published":"2025-12-11"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"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":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-06-03","vendors":["danny-avila"]},"summary":"Authenticated users can exfiltrate server secrets like JWT keys and database credentials by injecting environment variable references into MCP server URLs.","url":"https://insights.sbomify.com/CVE-2026-32625/"}