CVE-2026-34938NVD

Vulnerability Summary

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.

Severity Level

CRITICAL(10.0)

Published Date

Apr 3, 2026

Last Modified

Jul 24, 2026

Exploitation Status

No confirmed exploitation yet

EPSS Score (30-Day)

1.30%Probability

Root Weakness (CWE)

CWE-693: Unknown/Unlisted Weakness ↗

Refer to the official MITRE database for detailed architectural specifications regarding this weakness.

CVSS v3.1 Base Metrics — Score 10.0 (CRITICAL)

Attack VectorNetwork

Attack ComplexityLow

Privileges RequiredNone

User InteractionNone

ScopeChanged

ConfidentialityHigh

IntegrityHigh

AvailabilityHigh

Affected & Patched Versions

Affected Versions

Praison Praisonaiagents < 1.5.90

Patched Versions

Praison Praisonaiagents 1.5.90

🎁7-Day Free Trial — Try Pro or Team, no card required.

📧Email Delivery — Threat intel straight to your inbox.

♾️Unlimited Vendors — Track your entire stack.

🚨All New CVEs — Be the first to know.

📈EPSS Spike Alerts — Catch rising risk before it peaks.

🎯Custom EPSS/CVSS — Filter noise, focus on risk.

🛡️Exploit Intel — A 2nd confirmed-exploit signal beyond KEV.

🐙GitHub Issues — Auto-tracked, no duplicates.

📬Weekly Digest — One clean summary, not inbox spam.

🏷️Watchlist Groups — Tag alerts by team (Infra/AppSec/SOC).

💬Webhooks — Slack & Teams integration.

🔀Smart Routing — Critical alerts to one channel, rest to another.

🚫Ad-Free — Uninterrupted experience.