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?
EPSS puts the probability of exploitation in the next 30 days at 15.2%, higher than 97% of all known CVEs. Patch or mitigate before the next change window.
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
- 15.24% probability · 97th percentile
- Public exploits
- 1 in Exploit-DB · first 11 August 2026
- CISA KEV
- Not listed
- Weakness
- CWE-94
- Source
- disclosure@vulncheck.com
EPSS moved from 15.2% on 26 October 2026 to 15.2% on 30 October 2026. The dashed line is the ten per cent mark our analysts treat as “patch before the next change window”.
Public exploits (1)
Entries in Exploit-DB that cite this CVE. Links go to the Exploit-DB page and to the file in the public repository; nothing is hosted here. A verified tick means the Exploit-DB team confirmed the exploit works against the stated version.
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.