{"api_version":"1","generated_at":"2026-11-06T00:18:08+00:00","cve":"CVE-2026-57142","urls":{"html":"https://cve.report/CVE-2026-57142","api":"https://cve.report/api/cve/CVE-2026-57142.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-57142","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-57142"},"summary":{"title":"PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml","description":"PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow_dangerous_tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path loads workflow.yaml with YAMLWorkflowParser. That parser resolves agent-level tools: declarations and preserves top-level approve:. Workflow.start() then installs those YAML-approved tools into the approval context. As a result, an untrusted recipe can omit execute_command from TEMPLATE.yaml requires.tools, declare it in workflow.yaml agents.*.tools, and add top-level approve: [execute_command]. The caller did not set allow_dangerous_tools=True, but the recipe policy allows the recipe and the workflow approval path self-approves the critical shell tool. This issue has been patched in version 4.6.61.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-10-23 13:17:11","updated_at":"2026-10-29 14:17:57"},"problem_types":["CWE-78","CWE-94","CWE-863","CWE-78 CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')","CWE-863 CWE-863: Incorrect Authorization"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"7.8","severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","baseScore":7.8,"baseSeverity":"HIGH","attackVector":"LOCAL","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"7.8","severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","data":{"attackComplexity":"LOW","attackVector":"LOCAL","availabilityImpact":"HIGH","baseScore":7.8,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"REQUIRED","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"}}],"references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2","name":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2","refsource":"134c704f-9b21-4f2e-91b3-4a467353bcc0","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-57142","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-57142","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"MervinPraison","product":"PraisonAI","version":"affected >= 4.5.87, < 4.6.61","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":{"cve_year":"2026","cve_id":"57142","cve":"CVE-2026-57142","epss":"0.001460000","percentile":"0.038360000","score_date":"2026-10-29","updated_at":"2026-10-30 00:05:33"},"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"adp":[{"metrics":[{"other":{"content":{"id":"CVE-2026-57142","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","timestamp":"2026-10-29T13:11:25.967639Z","version":"2.0.3"},"type":"ssvc"}}],"providerMetadata":{"dateUpdated":"2026-10-29T13:12:14.267Z","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP"},"references":[{"tags":["exploit"],"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2"}],"title":"CISA ADP Vulnrichment"}],"cna":{"affected":[{"product":"PraisonAI","vendor":"MervinPraison","versions":[{"status":"affected","version":">= 4.5.87, < 4.6.61"}]}],"descriptions":[{"lang":"en","value":"PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow_dangerous_tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path loads workflow.yaml with YAMLWorkflowParser. That parser resolves agent-level tools: declarations and preserves top-level approve:. Workflow.start() then installs those YAML-approved tools into the approval context. As a result, an untrusted recipe can omit execute_command from TEMPLATE.yaml requires.tools, declare it in workflow.yaml agents.*.tools, and add top-level approve: [execute_command]. The caller did not set allow_dangerous_tools=True, but the recipe policy allows the recipe and the workflow approval path self-approves the critical shell tool. This issue has been patched in version 4.6.61."}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"LOCAL","availabilityImpact":"HIGH","baseScore":7.8,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"REQUIRED","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-78","description":"CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-94","description":"CWE-94: Improper Control of Generation of Code ('Code Injection')","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-863","description":"CWE-863: Incorrect Authorization","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-10-23T12:07:46.547Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2","tags":["x_refsource_CONFIRM"],"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2"}],"source":{"advisory":"GHSA-7qw2-w5rc-37x2","discovery":"UNKNOWN"},"title":"PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-57142","datePublished":"2026-10-23T12:07:46.547Z","dateReserved":"2026-06-24T01:45:48.697Z","dateUpdated":"2026-10-29T13:12:14.267Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-10-23 13:17:11","lastModifiedDate":"2026-10-29 14:17:57","problem_types":["CWE-78","CWE-94","CWE-863","CWE-78 CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')","CWE-863 CWE-863: Incorrect Authorization"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","baseScore":7.8,"baseSeverity":"HIGH","attackVector":"LOCAL","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":1.8,"impactScore":5.9}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-10-29T13:11:25.967639Z","id":"CVE-2026-57142","options":[{"exploitation":"poc"},{"automatable":"no"},{"technicalImpact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"57142","Ordinal":"1","Title":"PraisonAI recipe workflow policy can be bypassed by declaring an","CVE":"CVE-2026-57142","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"57142","Ordinal":"1","NoteData":"PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow_dangerous_tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path loads workflow.yaml with YAMLWorkflowParser. That parser resolves agent-level tools: declarations and preserves top-level approve:. Workflow.start() then installs those YAML-approved tools into the approval context. As a result, an untrusted recipe can omit execute_command from TEMPLATE.yaml requires.tools, declare it in workflow.yaml agents.*.tools, and add top-level approve: [execute_command]. The caller did not set allow_dangerous_tools=True, but the recipe policy allows the recipe and the workflow approval path self-approves the critical shell tool. This issue has been patched in version 4.6.61.","Type":"Description","Title":"PraisonAI recipe workflow policy can be bypassed by declaring an"}]}}}