CVE-2026-40088CRITICAL 9.6EPSS p33.3%

CVE-2026-40088CVE-2026-40088

Description

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.

Scoring

CVSS 3.19.6 (CRITICAL)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
EPSS0.42% probability of exploitation · percentile 33.3% · 2026-06-18T12:00:27Z
Published2026-04-09
Last modified2026-04-16

Underlying weaknesses· 1

CWE-78

References

  1. https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121
  2. https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m

1

TypeTargetConfidenceTier
WeaknessImproper Neutralization of Special Elements used in an OS Command ('OS Command Injection')cwe-780%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
CVE-2026-40111
CVE
CVE-2026-40288
CVE
CVE-2026-34937
CVE
CVE-2026-41497
CVE
CVE-2026-39891
CVE
CVE-2026-34935
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.