PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override
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.
CVE-2026-56075
Primary source · Revision 1
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-56075
PraisonAI
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
Structured affected-version data
Original package identities and version rules from this source.
[
{
"vendor": "PraisonAI",
"product": "PraisonAI",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "4.5.128",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "4.5.128",
"versionType": "semver"
}
],
"packageURL": "pkg:pypi/praisonai",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-56075
Source reference:
/cveMetadata/cveId
Publisher severity
high
Source reference: /containers/cna/metrics
- Event
- #12752 · Revision 1
- Added to Heist Feed
- Publisher date