CVE-2026-61447: PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
- Is it exploited?
Not on CISA's list. CISA has not added it to the Known Exploited Vulnerabilities catalog as of . If CISA adds it, this page shows it as known exploited.
- How likely is exploitation in the next 30 days?
- 15.2%
EPSS score, percentile 96.8 of all scored records. A probability estimated by FIRST, not a report of exploitation.
- How severe?
- 10.0 Critical
CVSS v4.0 base score, given by the CNA
- What should I do?
CISA has set no required action, because the vulnerability is not in KEV.
- Which versions are affected?
Affected
- before 1.6.78
Unaffected 1.6.78
Source: CISA Known Exploited Vulnerabilities (KEV) catalog, 2026.10.28, as of ; FIRST Exploit Prediction Scoring System (EPSS), v2026.06.15, as of ; CVE List V5 (CVE Program), cve_2026-10-28_0000Z, as of . About the data.
What to do
Advisories and patches
Affected products and versions
As listed in the CVE record.
| Status | Versions |
|---|---|
| Affected | before 1.6.78 |
| Unaffected | 1.6.78 |
Versions not listed are: unaffected.
Versions the record lists as unaffected: 1.6.78.
Source: CVE List V5 (CVE Program), cve_2026-10-28_0000Z, as of . About the data.
About this vulnerability
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.
Summary: CVE record, as of .
- CISA has not added CVE-2026-61447 to its Known Exploited Vulnerabilities (KEV) catalog, as of 28 Oct 2026.
- The CVE record was published on 11 Jul 2026.
- The CVE record carries a CVSS v4.0 base score of 10.0 (Critical), given by its CNA.
- FIRST's EPSS model puts the probability of exploitation in the next 30 days at 15.2% (percentile 96.8), as of 28 Oct 2026. EPSS is a statistical estimate, not a report of exploitation.
- CISA's SSVC assessment in the CVE record: exploitation poc, automatable yes, technical impact total.
Source: CISA Known Exploited Vulnerabilities (KEV) catalog, 2026.10.28, as of ; CVE List V5 (CVE Program), cve_2026-10-28_0000Z, as of ; FIRST Exploit Prediction Scoring System (EPSS), v2026.06.15, as of . About the data.
Description
PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
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.
Source: CVE List V5 (CVE Program), cve_2026-10-28_0000Z, as of . About the data.
Weakness
CWE and CAPEC are maintained by MITRE; the entries are those named in the CVE record.
Timeline
| Date | Event |
|---|---|
| CVE record published | |
| CVE record last updated |