nvd.nist.govadvisoryCVE-2026-61447
CVE-2026-61447 describes a critical (CVSS 4.0 score 10.0) remote code execution vulnerability in PraisonAI versions before 1.6.78, rooted in CodeAgent._execute_python(), which runs LLM-generated Python code with no AST validation, import restrictions, or sandbox enforcement. An attacker who can influence the LLM's output via prompt injection can exfiltrate environment secrets and achieve arbitrary code execution on the host, making it a textbook agentic-code-execution flaw (CWE-94).
TL;DR Unsandboxed LLM-generated code execution in PraisonAI's CodeAgent enables prompt-injection-driven RCE (CVSS 10.0, CWE-94).
Organisations named here
- CWE-94
- GHSA-2xv2-w8cq-5gxw
CVEs named here
- CVE-2026-61447
Technologies named here
- PraisonAI
- PraisonAI before 1.6.78
- Python
- LLM
Techniques named here
- Prompt Injection
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle