{"answers":{"affected":"It affects 1 product.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-6331 exists.","fix":"No fix has been published for CVE-2024-6331 yet. Limit exposure of the affected software until one is available.","what":"CVE-2024-6331 is a high-severity code injection vulnerability in stitionai/devika, published on 4 Aug 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-2024-6331 and fix it if it is affected.\n\nWhat it is: CVE-2024-6331 is a high-severity code injection vulnerability in stitionai/devika, published on 4 Aug 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-2024-6331 exists.\n\nAffected product: stitionai/devika. 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-2024-6331/ (Markdown: https://insights.sbomify.com/CVE-2024-6331/index.md)","id":"CVE-2024-6331","markdown":"https://insights.sbomify.com/CVE-2024-6331/index.md","name":"CVE-2024-6331","record":{"aliases":["GHSA-699f-m7wm-gv75"],"analysis":{"component_type":"library","fix_type":"configuration_change","impacts":["data_read"],"network_reachable":"yes","non_default_config":true,"product_category":"AI agent framework","requires_auth":"none","summary":"Attackers can read sensitive files via prompt injection due to disabled safety settings in the Devika AI agent framework.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"@huntr_ai","cpe":[{"product":"devika","vendor":"stitionai"}],"cvss":{"score":7.5,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","version":"3.1"},"cwes":[{"id":"CWE-74","name":"Improper Neutralization of Special Elements in Output Used by a Downstream Component"}],"description":"stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":null,"headline":"Injection by Prompt Injection in stitionai/devika","id":"CVE-2024-6331","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"code_injection","year":"2024"},"n_packages":0,"n_references":1,"next":{"headline":"Missing authorization in Booking for Appointments and Events Calendar – Amelia","id":"CVE-2024-6332"},"packages":[],"prev":{"headline":"GEO my WordPress \u003c 4.4.0.2 - Unauthenticated RCE via LFI","id":"CVE-2024-6330"},"products":["stitionai/devika"],"published":"2024-08-04","related":[{"cvss_score":9.1,"headline":"Path traversal in n/a","id":"CVE-2024-40422","kev_date_added":null,"published":"2024-07-24"},{"cvss_score":9.1,"headline":"Path Traversal in stitionai/devika","id":"CVE-2024-5926","kev_date_added":null,"published":"2024-06-30"},{"cvss_score":8.1,"headline":"Data leak through CORS misconfiguration in stitionai/devika","id":"CVE-2024-5549","kev_date_added":null,"published":"2024-07-09"},{"cvss_score":8.1,"headline":"Stored XSS in stitionai/devika","id":"CVE-2024-5711","kev_date_added":null,"published":"2024-07-08"},{"cvss_score":8.1,"headline":"CSRF Vulnerability in stitionai/devika","id":"CVE-2024-5712","kev_date_added":null,"published":"2024-06-28"},{"cvss_score":7.6,"headline":"Unprotected WebSocket in stitionai/devika","id":"CVE-2024-5820","kev_date_added":null,"published":"2024-06-27"}],"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":"partial"},"state":"PUBLISHED","updated":"2024-08-30","vendors":["stitionai"]},"summary":"Attackers can read sensitive files via prompt injection due to disabled safety settings in the Devika AI agent framework.","url":"https://insights.sbomify.com/CVE-2024-6331/"}