CVE-2026-47395 Details
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.
A vulnerability in PraisonAI's direct-prompt CLI allows for local server-side request forgery (SSRF) by automatically expanding '@url:' mentions in the prompt text before executing commands. This issue is present in PraisonAI versions prior to 4.6.40 and in PraisonAI Agents versions prior to 1.6.40. The CLI fetches the response from the specified URL and injects it into the model's prompt context without any restrictions or approval, enabling the retrieval of localhost-only HTTP resources.
Users can update to PraisonAI version 4.6.40 or later and PraisonAI Agents version 1.6.40 or later to address this vulnerability.
Metrics
CVSS 4.0 Severity and Vector Strings:
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Jul 21, 2026CISA-ADP
Assessed Jul 21, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3 | CISA-ADP | AdvisoryExploitRemedyVendor |
| https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6 | [email protected] | Source CodeVendor |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | [email protected] | Issue TrackingVendor |
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3 | [email protected] | AdvisoryExploitRemedyVendor |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-200 | Exposure of Sensitive Information to an Unauthorized Actor | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| PraisonAI | <= 4.6.39 (semver) |
CPE
Remediation
| |
| PraisonAI Agents | <= 1.6.39 (semver) |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jul 21, 2026 | CVE Modified | CISA-ADP |
| Jul 21, 2026 | New CVE Received | [email protected] |
Volerion