{"answers":{"affected":"3 open source packages ship an affected version, including praisonai.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-57142 exists.","fix":"Upgrade praisonai to 4.6.61 or later.","what":"CVE-2026-57142 is a high-severity vulnerability in MervinPraison PraisonAI, published on 23 Oct 2026."},"fix_prompt":"Check this codebase for CVE-2026-57142 and fix it if it is affected.\n\nWhat it is: CVE-2026-57142 is a high-severity vulnerability in MervinPraison PraisonAI, published on 23 Oct 2026. \nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-57142 exists.\n\nAffected packages and fixed versions:\n- praisonai (PyPI): affected from 4.5.87; fixed in 4.6.61\n- praisonai (PyPI): affected from 4.5.87; fixed in 4.6.61\n- praisonai (PyPI): affected from 4.5.87; fixed in 4.6.61\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-57142/ (Markdown: https://insights.sbomify.com/CVE-2026-57142/index.md)","id":"CVE-2026-57142","markdown":"https://insights.sbomify.com/CVE-2026-57142/index.md","name":"CVE-2026-57142","record":{"aliases":["GHSA-7qw2-w5rc-37x2","PYSEC-2026-3505"],"analysis":null,"analysis_generated_by":null,"assigner":"GitHub_M","cpe":[],"cvss":{"score":7.8,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"},{"id":"CWE-863","name":"Incorrect Authorization"},{"id":"CWE-78","name":"Improper Neutralization of Special Elements used in an OS Command"}],"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.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":true,"headline":"PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml","id":"CVE-2026-57142","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":null,"year":"2026"},"n_packages":3,"n_references":1,"next":{"headline":"PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / search_web tools via attacker-controlled searxng_url parameter","id":"CVE-2026-57143"},"packages":[{"ecosystem":"PyPI","fixed":["4.6.61"],"introduced":["4.5.87"],"last_affected":[],"package":"praisonai","purl":null,"source":"GHSA-7qw2-w5rc-37x2"},{"ecosystem":"PyPI","fixed":["4.6.61"],"introduced":["4.5.87"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"GHSA-7qw2-w5rc-37x2"},{"ecosystem":"PyPI","fixed":["4.6.61"],"introduced":["4.5.87"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"PYSEC-2026-3505"}],"prev":{"headline":"PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool","id":"CVE-2026-57141"},"products":["PraisonAI"],"published":"2026-10-23","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-10-29","vendors":["MervinPraison"]},"summary":null,"url":"https://insights.sbomify.com/CVE-2026-57142/"}