PraisonAI is a multi-agent teams system.

Code

The project this record applies to. Exploit listings stay in References.

No public source repository is identified for this product.

Timeline

Detection, updates, and resolution for this record.

1. Apr 3, 2026 · NIST NVD

   Detected

   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.

2. Jul 24, 2026 · NIST NVD

   Updated

   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.

Affected

• cpe praison/praisonaiagentsversion unspecified

Sources

• CVE.orgVulnerability recordCVE-2026-34938

  Official CVE identifier

  cve.org
• NIST NVDVulnerability recordCVE-2026-34938

  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 wrapp

  nvd.nist.gov

References

• Exploit · github.com