# CVE-2026-57116: PraisonAI AgentOS authentication bypass in FastAPI deployment

Source: https://junglewise.ai/threats/cve-2026-57116-praisonai-agentos-remains-unauthenticated-after-incomplete-fix  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-23. Updated: 2026-10-23  
License: CC BY 4.0 with a link back

CVE-2026-57116 · Severity: critical · CVSS 9.8 · Published 2026-10-23

PraisonAI is a system for deploying multi-agent AI applications. Its AgentOS deployment component fails to authenticate API requests, allowing any network-reachable attacker to enumerate deployed agents and invoke them directly. This gives attackers access to the agents' tools, private instructions, memory, API integrations, and ability to make cost-bearing model calls without permission.

Technologies: [praisonai (PyPI)](https://junglewise.ai/threats/technologies/pypi-praisonai). Vendors: [PraisonAI](https://junglewise.ai/threats/vendors/praisonai), [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-57116 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-57116 being exploited in the wild.

**How severe is CVE-2026-57116?** Critical severity, with a CVSS score of 9.8, published 23 October 2026.

**Which products and versions are affected?** PraisonAI 4.2.1 to 4.6.57; praisonai (PyPI) ECOSYSTEM:introduced=4.2.1,fixed=4.6.59.

**Is there a fix for CVE-2026-57116?** Yes. praisonai (PyPI): upgrade to 4.6.59 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-57116 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-57116?** Check whether you run PraisonAI or praisonai (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- praisonai (PyPI): upgrade to 4.6.59 or later

  ```sh
  pip install "praisonai>=4.6.59"
  ```


## Technical details

AgentOS registers FastAPI routes for /api/agents (GET) and /api/chat (POST) without authentication middleware, API key checks, or bearer-token validation. The chat route directly invokes agent.chat(request.message) regardless of Authorization header presence or correctness. The vulnerability affects versions 4.2.1 through 4.6.57; unauthenticated or incorrectly-authorized requests achieve the same effect as legitimate ones, enabling arbitrary agent invocation.

## Affected products

- PraisonAI PraisonAI 4.2.1 to 4.6.57

## Identifiers

- CVE-2026-57116
- GHSA-892r-p3jq-jp24
- PYSEC-2026-3507

## Timeline

- 2026-06-17: disclosed
- 2026-06-17: patched: version 4.6.59

## References

- [https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-892r-p3jq-jp24](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-892r-p3jq-jp24)

## Related threats

- [PraisonAI authentication bypass in A2U event streaming](https://junglewise.ai/threats/cve-2026-57146-praisonai-a2u-incomplete-authentication-fix-leaves-current-serve)
- [PraisonAI sandbox escape when Landlock unavailable](https://junglewise.ai/threats/cve-2026-57144-praisonai-sandlocksandbox-falls-back-to-unrestricted-subprocess)
- [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)
- [PraisonAI shell command injection in compute-bridged file tools](https://junglewise.ai/threats/cve-2026-57117-praisonai-compute-bridged-file-tools-allow-shell-command)
- [PraisonAI Jobs webhook SSRF via DNS rebinding](https://junglewise.ai/threats/cve-2026-57114-praisonai-jobs-webhook-ssrf-protection-bypass-via-dns-rebinding)