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

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

8.6 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L

EPSS

• CVE-2026-44339: 0.36% estimated exploitation activity in the next 30 days; percentile 30.18 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, permallow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables that were never declared as tools. Details The vulnerable resolution path is in toolexecution.py. After searching declared tools and the registry, execution falls back to globals() and then main: If a callable is found, it is executed directly: The permission gate does not enforce a declared-tool allowlist by default. In…

Published by the source

11 May 2026, 13:59 UTC

Last modified by the source

13 Jul 2026, 16:43 UTC

Source last checked

26 Oct 2026, 13:41 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-gmjg-hv98-qggq

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-gmjg-hv98-qggq

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-44339

Advisory: PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
IDs: CVE-2026-44339, GHSA-gmjg-hv98-qggq
Record: https://patchnext.com/advisories/cve-2026-44339 (revision 2, source checked 26 Oct 2026, 13:41 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 8.6)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: praisonaiagents 1.6.37; praisonai 4.6.37. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI praisonaiagents: affected <= 1.6.36; fixed in 1.6.37
- PyPI praisonai: affected <= 4.6.36; fixed in 4.6.37

## Suggested inspection (read-only)
- `python -m pip show praisonaiagents`: prints the installed version. Run with the environment that serves production active.
- `python -m pip show praisonai`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on praisonaiagents, praisonai.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-gmjg-hv98-qggq (OSV record GHSA-gmjg-hv98-qggq lists affected ranges: PyPI praisonaiagents >=0 =0 <4.6.37 (fixed))
- Verified: https://github.com/advisories/GHSA-gmjg-hv98-qggq (GitHub-reviewed advisory GHSA-gmjg-hv98-qggq lists affected ranges: PyPI praisonaiagents >=0 =0 <=4.6.36)

Commands are suggestions: review each one before running it.