Skip to main content
VulnerabilityPublished Updated

CVE-2026-56075: PraisonAI · Incorrect Authorization

Affects PraisonAISource CVE Database V5

0
Compare

Public exploit available · CVSS 8.7 High : upgrade to 4.5.128 as a priority.

Data as of 8 Nov 2026, 14:34 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulnCheck)CVSS 4.08.7
CNA (VulnCheck)CVSS 3.18.8
CISA SSVC
Exploitation
Proof of concept is public or traded
Automatable
Attackers cannot reliably automate steps 1–4 of the kill chain
Technical impact
Total control over the software or total information disclosure

CISA SSVC assessment, 2026-06-22.

Patch
Available – fixed in 4.5.128
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

t = 0 is the CVE’s publication on cve.org

  1. Disclosed: evidence found.

    CVE published 18 Jun 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: evidence found.

    CISA SSVC: proof of concept public

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

Timeline

  1. CVE ID reserved

    by VulnCheck

    , 6 hours before disclosure

  2. CVE published

    on cve.org

    , t = 0

  3. CISA SSVC assessment

    proof of concept public

    , 4 days after disclosure

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CISA SSVC, the Metasploit, Exploit-DB and nuclei-templates index as of 8 Nov 2026.

What to do

Upgrade PraisonAI to 4.5.128.

Affected software

ProductAffectedFixed in
PraisonAIPraisonAIAffected
  • <4.5.128
Fixed in
  • 4.5.128
PyPIPraisonAIpkg:pypi/PraisonAIOther threatsAffected
  • <4.5.128
Fixed in
  • 4.5.128

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

Description

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

References

Community reviews

Loading reviews…