THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-2xv2-w8cq-5gxw (critical) — PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets

[GHSA] GHSA-2xv2-w8cq-5gxw (critical) — PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets

highgithub_advisoriesPublished 2026-10-08

GHSA-2xv2-w8cq-5gxw Severity: critical CVE: CVE-2026-61447

PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets

### Summary `CodeAgent._execute_python()` executes LLM-generated Python code in a subprocess with the complete parent-process environment (`os.environ.copy()`), zero AST validation, zero import restrictions, and no sandbox enforcement —

MITRE ATT&CK techniques

Indicators of compromise

Original source: https://github.com/advisories/GHSA-2xv2-w8cq-5gxw