{"answers":{"affected":"3 open source packages ship an affected version, including vanna.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-5826 exists.","fix":"No fix has been published for CVE-2024-5826 yet. Limit exposure of the affected software until one is available.","what":"CVE-2024-5826 is a critical code injection vulnerability in vanna-ai/vanna, published on 27 Jun 2024. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2024-5826 and fix it if it is affected.\n\nWhat it is: CVE-2024-5826 is a critical code injection vulnerability in vanna-ai/vanna, published on 27 Jun 2024. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-5826 exists.\n\nAffected packages and fixed versions:\n- vanna (PyPI): affected all versions up to 0.6.2; no fix listed\n- vanna (PyPI): affected all versions up to 0.6.2; no fix listed\n- vanna (PyPI): affected all versions up to 0.6.2; no fix listed\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-2024-5826/ (Markdown: https://insights.sbomify.com/CVE-2024-5826/index.md)","id":"CVE-2024-5826","markdown":"https://insights.sbomify.com/CVE-2024-5826/index.md","name":"CVE-2024-5826","record":{"aliases":["GHSA-rrqq-fv6m-692m","PYSEC-2026-562"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"Python AI library","requires_auth":"none","summary":"Attackers can achieve remote code execution on the backend server by exploiting prompt injection in the vanna.ask function due to lack of sandboxing.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"@huntr_ai","cpe":[],"cvss":{"score":9.8,"severity":"critical","source":"cna","vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.0"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":false,"headline":"Remote Code Execution via Prompt Injection in vanna-ai/vanna","id":"CVE-2024-5826","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2024"},"n_packages":3,"n_references":1,"next":{"headline":"Arbitrary File Write by Prompt Injection via DuckDB SQL in vanna-ai/vanna","id":"CVE-2024-5827"},"packages":[{"ecosystem":"PyPI","fixed":[],"introduced":["0"],"last_affected":["0.6.2"],"package":"vanna","purl":null,"source":"GHSA-rrqq-fv6m-692m"},{"ecosystem":"PyPI","fixed":[],"introduced":["0"],"last_affected":["0.6.2"],"package":"vanna","purl":"pkg:pypi/vanna","source":"GHSA-rrqq-fv6m-692m"},{"ecosystem":"PyPI","fixed":[],"introduced":["0"],"last_affected":["0.6.2"],"package":"vanna","purl":"pkg:pypi/vanna","source":"PYSEC-2026-562"}],"prev":{"headline":"This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.","id":"CVE-2024-5825"},"products":["vanna-ai/vanna"],"published":"2024-06-27","related":[],"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":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"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":"2025-10-15","vendors":["vanna-ai"]},"summary":"Attackers can achieve remote code execution on the backend server by exploiting prompt injection in the vanna.ask function due to lack of sandboxing.","url":"https://insights.sbomify.com/CVE-2024-5826/"}