CVE-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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (2.49%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 4.0
- 10.0 CRITICALCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 2.49% probability · 84th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-94
- Source
- disclosure@vulncheck.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.