# praisonai (PyPI) vulnerabilities Source: https://junglewise.ai/threats/technologies/pypi-praisonai Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 13 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/technologies/pypi-praisonai.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 120 vulnerabilities in praisonai (PyPI): 0 in the last 7 days and 39 in the last 90 days, 32 of them critical and 0 exploited in the wild. The most recent, CVE-2026-57146, was published on 23 October 2026. 15 vulnerabilities in the last four weeks, up 36% on the four before (11). 1 critical against 6. ## Counts - Last 7 days: 0 - Last 30 days: 15 - Last 90 days: 39 - All time: 120 (32 critical, 0 exploited in the wild) ## Latest praisonai (PyPI) vulnerabilities - [CVE-2026-57146: PraisonAI authentication bypass in A2U event streaming](https://junglewise.ai/threats/cve-2026-57146-praisonai-a2u-incomplete-authentication-fix-leaves-current-serve) (high, CVSS 7.5, published 23 Oct 2026) - [CVE-2026-57144: PraisonAI sandbox escape when Landlock unavailable](https://junglewise.ai/threats/cve-2026-57144-praisonai-sandlocksandbox-falls-back-to-unrestricted-subprocess) (high, CVSS 8.8, published 23 Oct 2026) - [CVE-2026-57142: PraisonAI recipe policy bypass via YAML-approved tools](https://junglewise.ai/threats/cve-2026-57142-praisonai-recipe-workflow-policy-can-be-bypassed-by-declaring-and) (high, CVSS 7.8, published 23 Oct 2026) - [CVE-2026-57117: PraisonAI shell command injection in compute-bridged file tools](https://junglewise.ai/threats/cve-2026-57117-praisonai-compute-bridged-file-tools-allow-shell-command) (high, CVSS 8.8, published 23 Oct 2026) - [CVE-2026-57116: PraisonAI AgentOS authentication bypass in FastAPI deployment](https://junglewise.ai/threats/cve-2026-57116-praisonai-agentos-remains-unauthenticated-after-incomplete-fix) (critical, CVSS 9.8, published 23 Oct 2026) - [CVE-2026-57114: PraisonAI Jobs webhook SSRF via DNS rebinding](https://junglewise.ai/threats/cve-2026-57114-praisonai-jobs-webhook-ssrf-protection-bypass-via-dns-rebinding) (high, CVSS 7.2, published 23 Oct 2026) - [CVE-2026-57113: PraisonAI template loader path traversal in cache](https://junglewise.ai/threats/cve-2026-57113-praisonai-github-template-cache-path-traversal-allows-outside) (high, CVSS 8.1, published 23 Oct 2026) - [CVE-2026-56840: PraisonAI HTTPApproval dashboard XSS and auto-approval](https://junglewise.ai/threats/cve-2026-56840-praisonai-httpapproval-dashboard-renders-tool-arguments-as-raw) (high, CVSS 8.8, published 23 Oct 2026) - [CVE-2026-56838: PraisonAI recipe streaming bypasses dangerous tool policy check](https://junglewise.ai/threats/cve-2026-56838-praisonai-recipe-run-stream-skips-dangerous-tool-policy) (high, CVSS 7.8, published 23 Oct 2026) - [CVE-2026-56837: PraisonAI LinearBot missing webhook signature verification](https://junglewise.ai/threats/cve-2026-56837-praisonai-linearbot-processes-unsigned-webhooks-when-linear) (high, CVSS 8.6, published 23 Oct 2026) - [CVE-2026-56836: PraisonAI authentication bypass in Recipe Serve command](https://junglewise.ai/threats/cve-2026-56836-praisonai-recipe-serve-typer-command-bypasses-the-non-localhost) (high, CVSS 8.2, published 23 Oct 2026) - [CVE-2026-56835: PraisonAI authorization bypass in Slack app_mention handler](https://junglewise.ai/threats/cve-2026-56835-praisonai-slack-app-mention-bypasses-configured-user-channel) (high, CVSS 8.3, published 23 Oct 2026) - [CVE-2026-56834: PraisonAI arbitrary file read in artifact tools](https://junglewise.ai/threats/cve-2026-56834-praisonai-dynamic-context-artifact-tools-read-arbitrary-host) (high, CVSS 7.5, published 23 Oct 2026) - [CVE-2026-56833: PYSEC-2026-3499 - PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path…](https://junglewise.ai/threats/cve-2026-56833-praisonai-path-traversal-in-dynamic-context-history-and-terminal) (high, CVSS 7.5, published 23 Oct 2026) - [CVE-2026-56832: PraisonAI DiscordApproval dangerous tool authorization bypass](https://junglewise.ai/threats/cve-2026-56832-praisonai-discordapproval-accepts-unrelated-channel-messages-as) (high, CVSS 8.8, published 23 Oct 2026) - [CVE-2026-62176: PraisonAI code injection in deploy API server generation](https://junglewise.ai/threats/cve-2026-62176-praisonai-code-injection-via-f-string-interpolation-in-deploy-api) (critical, CVSS 9.1, published 7 Oct 2026) - [CVE-2026-57112: PraisonAI legacy SSE endpoint CORS and authentication bypass](https://junglewise.ai/threats/cve-2026-57112-praisonai-legacy-sse-endpoint-cors-and-authentication-bypass) (high, CVSS 8.3, published 15 Sep 2026) - [CVE-2026-57145: PraisonAI path traversal in multiedit tool](https://junglewise.ai/threats/cve-2026-57145-praisonai-path-traversal-in-multiedit-tool) (critical, CVSS 9.1, published 14 Sep 2026) - [CVE-2026-57132: PraisonAI authentication bypass with PRAISONAI_CALL_AUTH disabled](https://junglewise.ai/threats/cve-2026-57132-praisonai-authentication-bypass-with-praisonai-call-auth-disabled) (high, CVSS 8.2, published 14 Sep 2026) - [CVE-2026-57131: PraisonAI unauthenticated API access to jobs endpoint](https://junglewise.ai/threats/cve-2026-57131-praisonai-unauthenticated-api-access-to-jobs-endpoint) (critical, CVSS 9.8, published 14 Sep 2026) - [CVE-2026-57127: PraisonAI authentication bypass in recipe serve](https://junglewise.ai/threats/cve-2026-57127-praisonai-authentication-bypass-in-recipe-serve) (critical, CVSS 9.8, published 14 Sep 2026) - [CVE-2026-57124: PraisonAI unauthenticated remote code execution in MCP endpoint](https://junglewise.ai/threats/cve-2026-57124-praisonai-unauthenticated-remote-code-execution-in-mcp-endpoint) (critical, CVSS 9.8, published 14 Sep 2026) - [CVE-2026-57122: PraisonAI webhook authentication bypass in WhatsApp and Linear handlers](https://junglewise.ai/threats/cve-2026-57122-praisonai-webhook-authentication-bypass-in-whatsapp-and-linear) (high, CVSS 8.6, published 14 Sep 2026) - [CVE-2026-57119: PraisonAI Jobs API path traversal](https://junglewise.ai/threats/cve-2026-57119-praisonai-jobs-api-path-traversal) (high, CVSS 7.5, published 14 Sep 2026) - [CVE-2026-56839: PraisonAI path traversal in CODE_TOOLS helpers](https://junglewise.ai/threats/cve-2026-56839-praisonai-path-traversal-in-code-tools-helpers) (high, CVSS 7.3, published 14 Sep 2026) ## Most severe praisonai (PyPI) vulnerabilities - [Duplicate Advisory: PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets](https://junglewise.ai/threats/duplicate-advisory-praisonai-codeagent-executes-llm-generated-code-53937dc8) (critical, CVSS 10, published 11 Jul 2026) - [CVE-2026-47392: MervinPraison PraisonAI sandbox escape in execute_code tool](https://junglewise.ai/threats/cve-2026-47392-mervinpraison-praisonai-sandbox-escape-in-execute-code-tool) (critical, CVSS 9.9, published 21 Jul 2026) - [CVE-2026-61445: MervinPraison PraisonAI arbitrary file write and command execution in AICoder](https://junglewise.ai/threats/cve-2026-61445-mervinpraison-praisonai-arbitrary-file-write-and-command) (critical, CVSS 9.9, published 11 Jul 2026) - [Duplicate Advisory: PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Calls](https://junglewise.ai/threats/duplicate-advisory-praisonai-aicoder-arbitrary-file-write-and-command-869d28ba) (critical, CVSS 9.9, published 11 Jul 2026) - [CVE-2026-47391: MervinPraison PraisonAI remote code execution in A2A server example](https://junglewise.ai/threats/cve-2026-47391-mervinpraison-praisonai-remote-code-execution-in-a2a-server) (critical, CVSS 9.8, published 21 Jul 2026) - [CVE-2026-57124: PraisonAI unauthenticated remote code execution in MCP endpoint](https://junglewise.ai/threats/cve-2026-57124-praisonai-unauthenticated-remote-code-execution-in-mcp-endpoint) (critical, CVSS 9.8, published 14 Sep 2026) - [CVE-2026-34935: MervinPraison PraisonAI OS command injection in MCPHandler](https://junglewise.ai/threats/cve-2026-34935-mervinpraison-praisonai-os-command-injection-in-mcphandler) (critical, CVSS 9.8, published 3 Apr 2026) - [CVE-2026-57131: PraisonAI unauthenticated API access to jobs endpoint](https://junglewise.ai/threats/cve-2026-57131-praisonai-unauthenticated-api-access-to-jobs-endpoint) (critical, CVSS 9.8, published 14 Sep 2026) - [CVE-2026-57127: PraisonAI authentication bypass in recipe serve](https://junglewise.ai/threats/cve-2026-57127-praisonai-authentication-bypass-in-recipe-serve) (critical, CVSS 9.8, published 14 Sep 2026) - [CVE-2026-39890: MervinPraison PraisonAI RCE via YAML deserialization in AgentService](https://junglewise.ai/threats/cve-2026-39890-mervinpraison-praisonai-rce-via-yaml-deserialization-in) (critical, CVSS 9.8, published 8 Apr 2026) ## Vulnerabilities per week 15 vulnerabilities in the last four weeks, up 36% on the four before (11). 1 critical against 6. | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 13 | 1 | 0 | | 31 Aug 2026 | 0 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 10 | 5 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 0 | 0 | 0 | | 5 Oct 2026 | 1 | 1 | 0 | | 12 Oct 2026 | 0 | 0 | 0 | | 19 Oct 2026 | 15 | 1 | 0 | | 26 Oct 2026 | 0 | 0 | 0 | | 2 Nov 2026 | 0 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## Other PyPI technologies - [tensorflow (PyPI)](https://junglewise.ai/threats/technologies/pypi-tensorflow): 435 vulnerabilities - [tensorflow-cpu (PyPI)](https://junglewise.ai/threats/technologies/tensorflow-cpu): 430 vulnerabilities - [tensorflow-gpu (PyPI)](https://junglewise.ai/threats/technologies/tensorflow-gpu): 427 vulnerabilities - [open-webui (PyPI)](https://junglewise.ai/threats/technologies/open-webui): 177 vulnerabilities - [Django (PyPI)](https://junglewise.ai/threats/technologies/django): 173 vulnerabilities - [apache-airflow (PyPI)](https://junglewise.ai/threats/technologies/apache-airflow): 159 vulnerabilities - [pillow (PyPI)](https://junglewise.ai/threats/technologies/pillow): 125 vulnerabilities - [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm): 117 vulnerabilities - [plone (PyPI)](https://junglewise.ai/threats/technologies/pypi-plone): 101 vulnerabilities - [mlflow (PyPI)](https://junglewise.ai/threats/technologies/mlflow): 88 vulnerabilities - [picklescan (PyPI)](https://junglewise.ai/threats/technologies/picklescan): 86 vulnerabilities - [exiv2 (PyPI)](https://junglewise.ai/threats/technologies/exiv2): 85 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "praisonai (PyPI) vulnerabilities", https://junglewise.ai/threats/technologies/pypi-praisonai, 13 November 2026.