Auth bypass in Praisonai
CVE-2026-56075
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.
Vulnerability class: Broken Access Control
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.007 (51.6th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 52nd percentile — 51.6% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.007 · newest: 0.007 · change: 0.000
Affected products
- Praisonai — versions 0, 4.5.128
Weakness classification (CWE)
References
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm (vendor-advisory)
- www.vulncheck.com/advisories/praisonai-arbitrary-shell-command-execution-via-ha… (third-party-advisory)
Frequently asked questions
- What is CVE-2026-56075?
- CVE-2026-56075 is a high-severity vulnerability in Praisonai, classified under Incorrect Authorization. CVSS score: 8.8/10. Published 2026-06-18.
- How severe is CVE-2026-56075?
- High severity. CVSS v3 base score is 8.8 out of 10.