Skip to content
Fencer Vulns
high 7.9

CVE-2026-40149 json

PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

published 2026-04-09 7 mo ago modified 2026-10-26 13 d ago also EUVD-2026-21168 , GHSA-4wr3-f4p3-5wjh , PYSEC-2026-2901

cvss
7.9
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 14%
public exploits
0
none known

Summary

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g., shell_exec, file_write) to the allowlist, an attacker can cause the ExecApprovalManager to auto-approve all future agent invocations of those tools, bypassing the human-in-the-loop safety mechanism that the approval system is specifically designed to enforce. This vulnerability is fixed in 4.5.128.

Patch / fix

  • pypi praisonai 4.5.128
  • praison praisonai 4.5.128

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
6 mo ago

Exploit prediction

0.24% chance of exploitation in the next 30 days, higher than 14% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4wr3-f4p3-5wjh referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.9 CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N
GitHub 3.1 7.9 CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N
NVD 3.1 7.3 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:H/A:N
OSV 3.1 7.9 CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N

Affected packages

ecosystem package affected fixed in
pypi praisonai
<4.5.128
4.5.128

Affected products

  • MervinPraison PraisonAI

Classification

Weakness
  • CWE-396 Declaration of Catch for Generic Exception
  • CWE-306 Missing Authentication for Critical Functionality

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.