PraisonAI AgentLoop onToolCall approval runs after tool execution (CVE-2026-57137) | HOL Guard CVE

Unknown severity · Source severity not reportedCVE-2026-57137

PraisonAI AgentLoop onToolCall approval runs after tool execution

Answer in brief

CVE-2026-57137 records a Unknown severity vulnerability in PraisonAI AgentLoop onToolCall approval runs after tool execution. 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 Sep 15, 2026Updated Sep 15, 2026Source checked Sep 15, 2026First seen by HOL Sep 15, 2026Material review Sep 15, 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	>= 1.4.0, < 1.7.2	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
Sep 15, 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 15, 2026

Sources and claim methodology

Upstream source description

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.

Quoted source text, attributed separately from HOL analysis.