PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI automatically loads a file named tools.py from the current working directory to discover and register custom agent tools. This loading process uses importlib.util.spec_from_file_location and immediately executes module-level code via spec.loader.exec_module() without explicit user consent, validation, or sandboxing. The tools.py file is loaded implicitly, even when it is not referenced in configuration files or explicitly requested by the user. As a result, merely placing a file named tools.py in the working directory is sufficient to trigger code execution. This behavior violates the expected security boundary between user-controlled project files (e.g., YAML configurations) and executable code, as untrusted content in the working directory is treated as trusted and executed automatically. If an attacker can place a malicious tools.py file into a directory where a user or automated system (e.g., CI/CD pipeline) runs praisonai, arbitrary code execution occurs immediately upon startup, before any agent logic begins. This vulnerability is fixed in 4.5.128.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-426",
"CWE-829",
"CWE-94"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/40xxx/CVE-2026-40156.json"
}{
"cpe": "cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "4.5.128"
}
],
"source": [
"AFFECTED_FIELD",
"CPE_RANGE"
]
}