{"answers":{"affected":"3 open source packages ship an affected version, including praisonai and PraisonAI.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-47391 exists.","fix":"Upgrade praisonai to 4.6.40 or later.","what":"CVE-2026-47391 is a critical code injection vulnerability in MervinPraison PraisonAI, published on 21 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-47391 and fix it if it is affected.\n\nWhat it is: CVE-2026-47391 is a critical code injection vulnerability in MervinPraison PraisonAI, published on 21 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-47391 exists.\n\nAffected packages and fixed versions:\n- praisonai (PyPI): affected all versions; fixed in 4.6.40\n- praisonai (PyPI): affected all versions; fixed in 4.6.40\n- PraisonAI (PyPI): affected all versions; fixed in 4.6.40\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-2026-47391/ (Markdown: https://insights.sbomify.com/CVE-2026-47391/index.md)","id":"CVE-2026-47391","markdown":"https://insights.sbomify.com/CVE-2026-47391/index.md","name":"CVE-2026-47391","record":{"aliases":["GHSA-vg22-4gmj-prxw","PYSEC-2026-478"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution","data_read","data_modify"],"network_reachable":"yes","non_default_config":false,"product_category":"Python AI agent library","requires_auth":"none","summary":"Unauthenticated attackers can execute arbitrary Python code via the A2A example's eval-based tool, requiring an upgrade to secure the deployment.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":9.8,"severity":"critical","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-95","name":"Improper Neutralization of Directives in Dynamically Evaluated Code"},{"id":"CWE-306","name":"Missing Authentication for Critical Functionality"}],"description":"PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.","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's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution","id":"CVE-2026-47391","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":3,"next":{"headline":"PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)","id":"CVE-2026-47392"},"packages":[{"ecosystem":"PyPI","fixed":["4.6.40"],"introduced":["0"],"last_affected":[],"package":"PraisonAI","purl":null,"source":"GHSA-vg22-4gmj-prxw"},{"ecosystem":"PyPI","fixed":["4.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"GHSA-vg22-4gmj-prxw"},{"ecosystem":"PyPI","fixed":["4.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"PYSEC-2026-478"}],"prev":{"headline":"PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings","id":"CVE-2026-47390"},"products":["PraisonAI"],"published":"2026-07-21","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":"yes","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-07-23","vendors":["MervinPraison"]},"summary":"Unauthenticated attackers can execute arbitrary Python code via the A2A example's eval-based tool, requiring an upgrade to secure the deployment.","url":"https://insights.sbomify.com/CVE-2026-47391/"}