{"cve":"CVE-2026-57142","nvd":{"published":"2026-10-23T13:17:11.210","modified":"2026-10-23T13:17:11.330","status":"Deferred","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.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","score":7.8},"cwes":["CWE-78","CWE-94","CWE-863"],"references":["https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2"],"products":[],"source":"nvd","synced_at":"2026-10-23T16:39:28.036610720+00:00"},"epss":{"cve":"CVE-2026-57142","score":0.00146,"percentile":0.03816,"date":"2026-10-25"},"kev":null,"osv":[{"id":"GHSA-7qw2-w5rc-37x2","url":"https://osv.dev/vulnerability/GHSA-7qw2-w5rc-37x2","summary":"PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml","modified":"2026-07-23T15:11:22.645330452Z","packages":[{"ecosystem":"PyPI","name":"praisonai","purl":"pkg:pypi/praisonai","ranges":[">=4.5.87 <4.6.61"],"fixed":["4.6.61"]}]},{"id":"PYSEC-2026-3505","url":"https://osv.dev/vulnerability/PYSEC-2026-3505","summary":"PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml","modified":"2026-07-23T15:00:20.673849210Z","packages":[{"ecosystem":"PyPI","name":"praisonai","purl":"pkg:pypi/praisonai","ranges":[">=4.5.87 <4.6.61"],"fixed":["4.6.61"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}