Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-gfq8-hmph-9gjv

PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret

CVSS 8.2 HighEPSS 0.0049 · 42nd percentile

Published by the GitHub Advisory Database at 25 Aug 2026, 15:15 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
praisonaiPyPI<4.6.584.6.58
Identifiers
GHSA-gfq8-hmph-9gjv · CVE-2026-55533 · PYSEC-2026-3889
Weakness (CWE)
CWE-287 · CWE-306
Tags
Published
25 Aug 2026
Updated
10 Sept 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

PraisonAI versions before 4.6.58 (PyPI package praisonai) have an authentication fail-open issue in the Recipe HTTP server. When auth is set to api-key or jwt but no API key or JWT secret is configured, the server accepts unauthenticated requests to recipe run, stream, and validate endpoints, and to the admin reload endpoint if enabled. An attacker with network access to a Recipe server bound to a non-localhost interface can run recipe workflows or trigger reloads without credentials. Upgrade to version 4.6.58 or later.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
8.2 High 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0049, the 42nd percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:10 UTC First seen by agentprime
  2. 31 Oct 2026, 14:10 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.