{"id":"CVE-2026-57137","title":"PraisonAI is a multi-agent teams system","summary":"PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped A…","severity":"high","cvss":8.8,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H","cwe":["CWE-693","CWE-862","CWE-863"],"vendor":"MervinPraison","product":"PraisonAI","affected":["PraisonAI >= 1.4.0, < 1.7.2"],"published":"2026-09-15","updated":"2026-09-15","sourceUpdated":"2026-09-15T14:45:28.563","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-57137","references":[{"url":"https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9","label":"security-advisories@github.com"},{"url":"https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62","label":"security-advisories@github.com"},{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4","label":"security-advisories@github.com"},{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4","label":"134c704f-9b21-4f2e-91b3-4a467353bcc0"}],"tags":["nvd","cve.org","exploit-available"],"epss":0.0036,"epssPercentile":0.29734,"exploitAvailable":true,"ssvc":{"exploitation":"poc","automatable":"no","technicalImpact":"total","timestamp":"2026-09-15T12:44:54.123919Z"},"ingestedAt":"2026-09-15T10:35:28.519Z","slug":"CVE-2026-57137","body":"## Overview\n\nPraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.","depth":"midnight","depthScore":60,"depthScoreParts":{"impact":48.4,"likelihood":0.1,"exploitation":12,"ransomware":0},"changes":[{"seq":203603,"id":"CVE-2026-57137","ts":1789479488065,"field":"exploit_available","old":"false","new":"true"}]}