{"id":"CVE-2026-61439","title":"PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked","summary":"PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector promp…","severity":"high","cvss":7.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","cwe":["CWE-1188"],"published":"2026-07-11","updated":"2026-07-11","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-61439","references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fj8f-m44g-c479","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/praisonai-before-prompt-injection-defense-bypass","label":"disclosure@vulncheck.com"}],"tags":["nvd"],"ingestedAt":"2026-07-11T23:16:21.350Z","epss":0.00432,"epssPercentile":0.37033,"slug":"CVE-2026-61439","body":"## Overview\n\nPraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.","depth":"twilight","depthScore":41,"depthScoreParts":{"impact":41.3,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}