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

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). Vendors: PraisonAI, 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
    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

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.