SEPTEMBER 7, 2026
Live Feed
Back to database
Case File

CVE-2026-47395

MEDIUM · CVSS 5.5 EPSS 0.13% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-21 · Last synced 2026-08-20

CyberRota Analysis

AI-Generated

PraisonAI versions prior to 4.6.40 are vulnerable due to a flaw in the direct-prompt CLI that allows arbitrary URLs to be fetched, including localhost resources, without any restrictions or approval. This could lead to the injection of potentially malicious content into the model's prompt context, posing a risk of data leakage or unintended command execution. Organizations using PraisonAI should prioritize upgrading to the fixed versions to mitigate this risk.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-47395
Severity
MEDIUM
CVSS
5.5
EPSS
0.13%

Original NVD Description

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.