Critical · CVSS 9.8CVE-2026-57125

PraisonAI: Unauthenticated RCE via Jobs API + Approval BypassCVE-2026-57125

Answer in brief

CVE-2026-57125 records a Critical severity (CVSS 9.8) vulnerability in PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass. The current sources do not mark it as known exploited. The current feed maps MervinPraison/PraisonAI (generic), MervinPraison/praisonaiagents (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 Sep 14, 2026Updated Sep 15, 2026Source checked Oct 29, 2026First seen by HOL Sep 14, 2026Material review Sep 15, 2026

Upstream Advisory

Key facts

Risk: Critical · CVSS 9.8
Exploitation: Not marked as known exploited
Affected software: 2 mapped packages or products
Fix availability: Available

Why this deserves its current priority

CVSS is 9.8. 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), MervinPraison/praisonaiagents (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
MervinPraison/PraisonAIgeneric	<4.6.59	4.6.59
MervinPraison/praisonaiagentsgeneric	<1.6.59	1.6.59

Recommended response

Check inventory. Check lockfiles and deployed manifests for MervinPraison/PraisonAI, MervinPraison/praisonaiagents.
Review the reported fix. Update MervinPraison/PraisonAI to 4.6.59; MervinPraison/praisonaiagents to 1.6.59 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

Published upstream
Sep 14, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Sep 15, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Sep 14, 2026

Sources and claim methodology

Upstream source description

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.

Quoted source text, attributed separately from HOL analysis.