CVE-2026-56075

PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

CVSS 8.7 HIGHEPSS 0.5%CWE-863

Vexday Risk Score

21Low

SSVC decision (CISA)

Track

No exploitation signal → monitor

CVSS 8.7EPSS 0.5%KEV nãoPoC —Nuclei —Metasploit —Patch referenciado

Lifecycle

18 Jun 2026Published on NVD

Recommendation: Monitor — no exploitation signal at the moment.

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.

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

Affected products

PraisonAI · PraisonAI

Want to know if your infrastructure is exposed to this?

Talk to TrueHacking →

References

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm https://www.vulncheck.com/advisories/praisonai-arbitrary-shell-command-execution-via-hardcoded-approval-mode-override