PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server (CVE-2026-55532) | HOL Guard CVE

Unknown severity · Source severity not reportedCVE-2026-55532

PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

Answer in brief

CVE-2026-55532 records a Unknown severity vulnerability in PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server. The current sources do not mark it as known exploited. The current feed maps MervinPraison/PraisonAI (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Aug 25, 2026Updated Aug 25, 2026Source checked Aug 25, 2026First seen by HOL Aug 25, 2026Material review Aug 25, 2026

Upstream Advisory

Key facts

Risk: Unknown severitySource severity not reported
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Not reported

Why this deserves its current priority

A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps MervinPraison/PraisonAI (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
MervinPraison/PraisonAIgeneric	< 4.6.58	Not reported

Recommended response

Check inventory. Check lockfiles and deployed manifests for MervinPraison/PraisonAI.
Review the reported fix. Monitor this advisory for an available fix and review any installs of the affected package.

Evidence timeline and material changes

Published upstream
Aug 25, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Aug 25, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Aug 25, 2026

Sources and claim methodology

Upstream source description

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and invoke tools/call without an API key, including file writes that persist agent instructions. This issue is fixed in version 4.6.58.

Quoted source text, attributed separately from HOL analysis.