CVE-2026-61447
CWE-94Published: July 11, 2026· Updated: Jul 13, 2026
Official 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.
Risk Analysis
This critical vulnerability in PraisonAI allows attackers to execute arbitrary code on the host system and steal sensitive environment secrets. The flaw stems from the application's failure to properly validate or sandbox Python code generated by its AI, making it highly urgent due to its perfect CVSS score of 10.0.
No public exploit is currently known for this vulnerability. However, its remote exploitability and low attack complexity make it a significant concern.
Upgrade PraisonAI to version 1.6.78 or later to address the vulnerability. Implement robust input validation and consider sandboxing AI-generated code in your environment.
Technical Analysis
CVE-2026-61447 can be exploited remotely over the network without requiring physical or adjacent access, significantly expanding the attack surface for threat actors.
The vulnerability requires no privileges and no user interaction, making it a prime target for automated exploitation campaigns and worm-like propagation.
A successful exploit results in complete confidentiality breach (data exposure), full integrity compromise (data manipulation), availability disruption (denial of service), with a CVSS base score of 10.0.
The vulnerability has a "Changed" scope, meaning successful exploitation can impact components beyond the vulnerable component itself — such as the host operating system or adjacent services.
CVSS v3.1 Vector Breakdown
Affected Vendors & Products
Exploit & PoC Resources
All References (3)
Quick Facts
Related CVEs (CWE-94)
Recommended Actions
- →Apply vendor patches immediately
- →Monitor CVE-2026-61447 in threat intel feeds
- →Review IDS/IPS signatures for exploitation attempts