ZDF
Sign inSign up

Vulnerabilities

Vulnerability · CVE-2026-61447

PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

Published Jul 11, 2026 · catalog updated Jul 13, 2026 · MervinPraison PraisonAI

Last checked Oct 29, 2026. A connected source was read within the last 7 days.

Check this week

CVE-2026-61447 is not in CISA KEV. FIRST estimates a 15.24% chance of exploitation in the next 30 days. Check whether you run MervinPraison PraisonAI.

Gaps on this record

  • No version range is stored. A customer cannot check an installed version against this record.
  • No vendor fix or required action is stored. Compare the linked advisory before you change production.

Same product and reporting

Severity
Critical10.0
Known exploitation
Not in CISA/VulnCheck KEV
EPSS
15.24%
Remediation
Advisory link
Affected products
vendor MervinPraison PraisonAI

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

Are you affected?

Enter the version you run. The result uses only the ranges stored on this record.

The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.

  • vendor MervinPraison PraisonAIversion unspecified

How to fix CVE-2026-61447

What to do

Three questions, each answered from this record only. Confirm the vendor advisory before you patch.

Should you patch?

CVE-2026-61447 is not in CISA KEV. FIRST estimates a 15.24% chance of exploitation in the next 30 days. Check whether you run MervinPraison PraisonAI.

Which versions are affected?

Affected version ranges are not on this record. Compare the installed version with the linked vendor advisory before you change production.

What should an analyst verify?

CWE-94: Code Injection. EPSS 15.24%. There is no CISA KEV listing. A public exploit reference is linked in Sources. That is not the same as confirmed exploitation. Use the source links for the original advisory.

Code

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

Timeline

Detection, updates, and resolution for this record.

  1. Jul 13, 2026 · CVE.org

    Updated

    PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

  2. Oct 25, 2026 · Tenable CVE Database

    Detected

    PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

Sources

  • CVE.orgVulnerability recordCVE-2026-61447

    PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfilt

    cve.org
  • FIRST EPSSExploitation probabilityCVE-2026-61447

    30-day exploitation probability 15.24%

    first.org
  • Exploit DatabasePublic exploit reference52639

    Public exploit archive reference. This is not confirmation of exploitation. The exploit body is not stored here.

    exploit-db.com
  • Tenable CVE DatabaseVulnerability recordCVE-2026-61447

    PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

    tenable.com

References

Freshness

Last verified in this catalog Oct 29, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.

  • FIRST EPSSOct 29, 2026
  • Exploit DatabaseOct 27, 2026
  • CVE.orgOct 26, 2026
  • Tenable CVE DatabaseOct 26, 2026