Analysis and contextual insights are available on OpenCVE Cloud.
No vendor fix or workaround currently provided.
Additional remediation guidance may be available on OpenCVE Cloud.
Tracking
Sign in to view the affected projects.
| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-h2w2-v7j6-xqm4 | npm PraisonAI AgentLoop onToolCall approval runs after tool execution |
Tue, 15 Sep 2026 13:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
Tue, 15 Sep 2026 12:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Mervinpraison
Mervinpraison praisonai |
|
| Vendors & Products |
Mervinpraison
Mervinpraison praisonai |
Tue, 15 Sep 2026 10:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | PraisonAI AgentLoop onToolCall approval runs after tool execution | |
| Weaknesses | CWE-693 CWE-862 CWE-863 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-09-15T12:46:04.174Z
Reserved: 2026-06-24T01:45:48.696Z
Link: CVE-2026-57137
Updated: 2026-09-15T12:45:10.885Z
Status : Received
Published: 2026-09-15T11:17:11.030
Modified: 2026-09-15T13:16:43.213
Link: CVE-2026-57137
No data.
OpenCVE Enrichment
Updated: 2026-09-15T11:45:17Z
Github GHSA