{"id":"CVE-2026-40149","aliases":["GHSA-4wr3-f4p3-5wjh","PYSEC-2026-2901"],"url":"https://o3.security/vulnerability/CVE-2026-40149","summary":"PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls","details":"PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g., shell_exec, file_write) to the allowlist, an attacker can cause the ExecApprovalManager to auto-approve all future agent invocations of those tools, bypassing the human-in-the-loop safety mechanism that the approval system is specifically designed to enforce. This vulnerability is fixed in 4.5.128.","published":"2026-04-09T21:23:03.831Z","modified":"2026-08-07T11:50:17.025022461Z","cvss":{"score":7.9,"severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N"},"epss":null,"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"praisonai","fixedVersion":"4.5.128"}],"fix":null,"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/40xxx/CVE-2026-40149.json"},{"type":"ADVISORY","url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4wr3-f4p3-5wjh"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-40149"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-07T11:50:17.025022461Z"}}