{"answers":{"affected":"2 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-2026-57133 exists.","fix":"Upgrade praisonai to 1.7.2 or later.","what":"CVE-2026-57133 is a high-severity command injection vulnerability in MervinPraison PraisonAI, published on 15 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-57133 and fix it if it is affected.\n\nWhat it is: CVE-2026-57133 is a high-severity command injection vulnerability in MervinPraison PraisonAI, published on 15 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-57133 exists.\n\nAffected packages and fixed versions:\n- praisonai (npm): affected from 1.5.1; fixed in 1.7.2\n- praisonai (npm): affected from 1.5.1; fixed in 1.7.2\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-2026-57133/ (Markdown: https://insights.sbomify.com/CVE-2026-57133/index.md)","id":"CVE-2026-57133","markdown":"https://insights.sbomify.com/CVE-2026-57133/index.md","name":"CVE-2026-57133","record":{"aliases":["GHSA-5jv7-2mjm-h6qj"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"PraisonAI npm library","requires_auth":"low_privilege","summary":"Attackers can execute arbitrary commands by chaining shell syntax to allowlisted commands in PraisonAI's utility tools.","user_interaction":"not_required","vuln_class":"command_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":8.8,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-863","name":"Incorrect Authorization"},{"id":"CWE-78","name":"Improper Neutralization of Special Elements used in an OS Command"},{"id":"CWE-693","name":"Protection Mechanism Failure"}],"description":"PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2.","ecosystems":["npm"],"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 utility shell safe-command wrapper allowlist bypass via shell chaining","id":"CVE-2026-57133","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"npm","product":null,"products":[],"type":"command_injection","year":"2026"},"n_packages":2,"n_references":3,"next":{"headline":"PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation","id":"CVE-2026-57134"},"packages":[{"ecosystem":"npm","fixed":["1.7.2"],"introduced":["1.5.1"],"last_affected":[],"package":"praisonai","purl":null,"source":"GHSA-5jv7-2mjm-h6qj"},{"ecosystem":"npm","fixed":["1.7.2"],"introduced":["1.5.1"],"last_affected":[],"package":"praisonai","purl":"pkg:npm/praisonai","source":"GHSA-5jv7-2mjm-h6qj"}],"prev":{"headline":"PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication","id":"CVE-2026-57132"},"products":["PraisonAI"],"published":"2026-09-15","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":"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":"2026-09-16","vendors":["MervinPraison"]},"summary":"Attackers can execute arbitrary commands by chaining shell syntax to allowlisted commands in PraisonAI's utility tools.","url":"https://insights.sbomify.com/CVE-2026-57133/"}