PraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI Endpoint
PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: * headers, combined with Starlette's Content-Type-agnostic JSON parsing, enabling attackers to bypass CORS preflight checks via simple requests and exfiltrate sensitive agent responses including tool execution results and environment data.
CVE-2026-56076
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-2026-56076
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": "1.5.128",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "1.5.128",
"versionType": "semver"
}
],
"packageURL": "pkg:pypi/praisonaiagents",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-56076
Source reference:
/cveMetadata/cveId
Publisher severity
high
Source reference: /containers/cna/metrics
- Event
- #12753 · Revision 1
- Added to Heist Feed
- Publisher date