PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-863"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/56xxx/CVE-2026-56075.json"
}{
"extracted_events": [
{
"range": [
{
"introduced": "0"
},
{
"fixed": "4.5.128"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"range": [
{
"introduced": "0"
},
{
"fixed": "4.5.128"
}
],
"source": "DESCRIPTION"
}
]
}