{"id":"CVE-2026-51871","published":"2026-09-30T21:17:12.947","lastModified":"2026-10-01T17:17:26.300","description":"Devika v1.0 is vulnerable to Code Injection in the Runner.execute function in src/agents/runner/runner.py which allows an attacker to achieve arbitrary code execution by exploiting the direct execution of LLM-generated content.","cvssScore":9.8,"cvssSeverity":"CRITICAL","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","cwes":["CWE-94"],"vendors":[],"products":[],"references":[{"url":"https://gist.github.com/Ro1ME/3067a5bd69dcd35ffc98dc41ca611242","tags":[]},{"url":"https://github.com/stitionai/devika/issues/714","tags":[]},{"url":"https://gist.github.com/Ro1ME/3067a5bd69dcd35ffc98dc41ca611242","tags":[]}],"exploitRefs":[{"url":"https://gist.github.com/Ro1ME/3067a5bd69dcd35ffc98dc41ca611242","tags":[]},{"url":"https://github.com/stitionai/devika/issues/714","tags":[]},{"url":"https://gist.github.com/Ro1ME/3067a5bd69dcd35ffc98dc41ca611242","tags":[]}],"hasPoc":true,"ai":{"summary":"Devika v1.0 is vulnerable to arbitrary code execution due to direct execution of LLM-generated content, allowing attackers to inject malicious code.","exploitability":"Exploitation is relatively straightforward given the direct execution of user input, requiring only LLM-generated content to be manipulated.","blast_radius":"If exploited, this flaw could lead to complete control over the Devika system, including data theft and system compromise.","remediation":"Upgrade to the latest version of Devika, ensuring it includes the necessary security patches.","detection":"No reliable host or network indicator is derivable from the published description.","tags":["rce","llm","code-injection","patch-required","security-update"],"model":"qwen2.5:7b-instruct","analyzedAt":"2026-10-02T08:41:29.682Z"}}