CVE-2026-61447
Description
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.
Severity
CRITICAL
CVSS v3
10.0
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H · source cna
CVSS v4
10.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H · source cna
Exploit chance (EPSS)
15.240%
chance of exploitation in the next 30 days
higher than 96.8% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 0
Metasploit modules: 0
Nuclei templates: 0
Exploit-DB: 1
Weakness
- CWE-94: Improper Control of Generation of Code
CISA SSVC decision points
| Exploitation | poc |
|---|---|
| Automatable | yes |
| Technical impact | total |
| Scored | 2026-07-13 |
Timeline
- 2026-07-11Published by the CNA13:01 UTC
- 2026-07-13CISA SSVC decision recorded2 days after publication
- 2026-08-11First Exploit-DB entry (EDB-ID 52639)31 days after publication
- 2026-10-08GitHub advisory published (GHSA-2xv2-w8cq-5gxw)89 days after publication
Exploit and advisory records
| Exploit-DB | Type | Platform | Published | EDB-verified |
|---|---|---|---|---|
| EDB-ID 52639 | remote | multiple | 2026-08-11 | no |
GitHub advisory GHSA-2xv2-w8cq-5gxw, affected packages:
| Package | Vulnerable versions | Fixed in |
|---|---|---|
| PyPI praisonaiagents | before 1.6.78 | 1.6.78 |
Affected products
Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.
| Product | Vulnerable versions | Fixed in |
|---|---|---|
| mervinpraison praisonai | from 0 before 1.6.78fixed in 1.6.78 | 1.6.78 |
| praison praisonai | before 1.6.78fixed in 1.6.78 | 1.6.78 |
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2xv2-w8cq-5gxw
- https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-codeagent
Get more CVE data from the API.
curl 'https://api.contrastcyber.com/cve_lookup/CVE-2026-61447'curl 'https://api.contrastcyber.com/cve_risk_score/CVE-2026-61447'curl 'https://api.contrastcyber.com/cve_exploit/CVE-2026-61447'curl 'https://api.contrastcyber.com/cve_products/CVE-2026-61447'
Sources
- Vulnerability data from the National Vulnerability Database (NIST) and the CVE Program. CVE records: Copyright © 1999-2026, The MITRE Corporation, used under the CVE Program Terms of Use. CVE® is a registered trademark of The MITRE Corporation.
- CWE definitions: Copyright © 2006-2026, The MITRE Corporation, used under the CWE Terms of Use. CWE is a trademark of The MITRE Corporation.
- OWASP Top 10 categories by the OWASP Foundation (CC BY 3.0).
- EPSS scores by FIRST.org EPSS, used with attribution.
- KEV catalog and SSVC decisions by CISA.
- Advisory data from the GitHub Advisory Database through OSV.dev (CC BY 4.0).
- Exploit metadata from the Exploit Database (GPL-2.0-only, metadata only).
- Nuclei template names from nuclei-templates (MIT).