Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-hc5v-gxvj-58wh

PraisonAI: MCP HTTP-stream transport is unauthenticated by default, exposing tool enumeration and an unvalidated tool-call surface

CVSS 6.9 MediumEPSS 0.0043 · 37th percentile

Published by the GitHub Advisory Database at 8 Oct 2026, 21:58 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
praisonaiPyPI<4.6.784.6.78
Identifiers
GHSA-hc5v-gxvj-58wh · CVE-2026-61427 · PYSEC-2026-4257
Weakness (CWE)
CWE-20 · CWE-306 · CWE-862
Tags
Published
8 Oct 2026
Updated
15 Oct 2026

Machine-written summary

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

PraisonAI versions before 4.6.78 expose their MCP HTTP-stream server without authentication when no API key is configured, which is the default for the CLI's `--api-key` option. An unauthenticated client that can reach the server can list about 50 tools and send tool calls whose arguments are not checked against the tools' declared schemas. The source reports no confirmed remote code execution or file read. Upgrade to version 4.6.78 or later, or start the server with an API key set.

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
6.9 Medium 4.0 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N CNA (VulnCheck)
  • CISA KEV Not listed.
  • EPSS 0.0043, the 37th percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:08 UTC First seen by agentprime
  2. 31 Oct 2026, 14:08 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.