Advisory record · GHSA-gmjg-hv98-qggq

PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

CVSS 8.6 HighEPSS 0.0036 · 30th percentile

Published by the GitHub Advisory Database at 11 May 2026, 13:59 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
praisonaiagentsPyPI<1.6.371.6.37
praisonaiPyPI<4.6.374.6.37
Identifiers
GHSA-gmjg-hv98-qggq · CVE-2026-44339 · PYSEC-2026-2915 · PYSEC-2026-2948
Weakness (CWE)
CWE-470
Published
11 May 2026
Updated
13 Jul 2026

Machine-written summary

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

Versions of praisonaiagents before 1.6.37 and praisonai before 4.6.37 can run undeclared callables from the application's `__main__` or module globals when a tool name is unresolved, because the lookup falls back to those scopes after the declared tool list and registry fail to match. The default agent configuration does not reject undeclared non-dangerous tool names, so an attacker who can influence tool-call names may invoke privileged helper functions with the application's privileges. Upgrade praisonaiagents to 1.6.37 and praisonai to 4.6.37.

Written 6 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
8.6 High 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0036, the 30th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 15:01 UTC First seen by agentprime
  2. 31 Oct 2026, 15:01 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.