Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-57137— PraisonAI AgentLoop onToolCall approval runs after tool execution

Quick assessment

Affected
MervinPraison PraisonAI
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

PraisonAI 是一个多智能体协作系统。在 1.4.0 至 1.7.2 版本中， 中的 在调用 审批回调之前，就将可执行工具传递给了 。由于封装的 AI SDK 在生成过程中会执行工具处理器，当该回调返回 （表示拒绝）时，系统仅在已产生副作用且已填充 的已拒绝工具执行之后，才记录 。因此，使用 作为人工或策略审批边界的应用程序，可能会执行已被拒绝的文件、命令、API 调用或数据修改操作。该问题已在 1.7.2 版本中修复。

CVSS 8.8 · High
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-57137

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
PraisonAI AgentLoop onToolCall approval runs after tool execution
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
保护机制失效
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
MervinPraison PraisonAI >= 1.4.0, < 1.7.2 -

II. Public POCs for CVE-2026-57137

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-57137

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-57137 (1)

Vendor Pages for CVE-2026-57137 (1)

Same Patch Batch · MervinPraison · 2026-09-15 · 12 CVEs total

CVE-2026-57138 9.9 CRITICAL PraisonAI codeMode sandbox escape via Function constructor
CVE-2026-57139 9.8 CRITICAL PraisonAI MCPServer exposes unauthenticated HTTP tools/call
CVE-2026-57141 9.8 CRITICAL PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool
CVE-2026-57147 9.8 CRITICAL praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forger
CVE-2026-57148 9.8 CRITICAL praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (def
CVE-2026-57140 9.4 CRITICAL PraisonAI AgentOS exposes unauthenticated agent listing and invocation
CVE-2026-57133 8.8 HIGH PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining
CVE-2026-57136 8.8 HIGH PraisonAI SandboxExecutor allowedCommands bypass via shell chaining
CVE-2026-57112 8.3 HIGH PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes reg
CVE-2026-57134 8.2 HIGH PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials witho
CVE-2026-57135 7.6 HIGH PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network cli

IV. Related Vulnerabilities

Same product: PraisonAI
Same vendor: MervinPraison
Same weakness: CWE-693

V. Comments for CVE-2026-57137

No comments yet

Leave a comment