Skip to content
Fencer Vulns
high 7.8

CVE-2026-55522 json

PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code

published 2026-08-05 3 mo ago modified 2026-10-24 15 d ago also EUVD-2026-53580 , GHSA-hxmv-c4g6-5fqc , PYSEC-2026-3891 , PYSEC-2026-3903

cvss
7.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 13%
public exploits
0
none known

Summary

PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow "include" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe's tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.

Patch / fix

  • pypi praisonaiagents 1.6.58
  • pypi praisonai 4.6.58
  • praison praisonai 4.6.58
  • praison praisonaiagents 1.6.58

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
3 mo ago

Exploit prediction

0.22% chance of exploitation in the next 30 days, higher than 13% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
GitHub 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
OSV 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi praisonaiagents
>=0.12.12, <1.6.58
1.6.58
pypi praisonai
>=3.9.26, <4.6.58
4.6.58

Affected products

  • MervinPraison PraisonAI
  • MervinPraison praisonaiagents

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code
  • CWE-426 Untrusted Search Path
  • CWE-829 Inclusion of Functionality from Untrusted Control Sphere

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.