{"id":"CVE-2026-61447","title":"PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement","summary":"PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LL…","severity":"critical","cvss":10,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","cwe":["CWE-94"],"published":"2026-07-11","updated":"2026-07-11","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-61447","references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-codeagent","label":"disclosure@vulncheck.com"}],"tags":["nvd","exploit-available"],"ingestedAt":"2026-07-11T23:16:21.397Z","epss":0.0249,"epssPercentile":0.83818,"exploitAvailable":true,"exploits":{"exploitdb":true,"checkedAt":"2026-09-21T15:29:53.415Z"},"slug":"CVE-2026-61447","body":"## Overview\n\nPraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.","depth":"abyssal","depthScore":67,"depthScoreParts":{"impact":55,"likelihood":0.5,"exploitation":12,"ransomware":0},"changes":[{"seq":128,"id":"CVE-2026-61447","ts":1786564763254,"field":"exploit_available","old":"false","new":"true"}]}