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.
Published: 2026-07-21
Score: 5.5 Medium
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

No analysis available yet.

Remediation

No remediation available yet.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-5cxw-77wg-jrf3 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
History

Tue, 21 Jul 2026 18:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Tue, 21 Jul 2026 16:00:00 +0000

Type Values Removed Values Added
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.
Title PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
Weaknesses CWE-200
References
Metrics cvssV3_1

{'score': 5.5, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N'}

Subscriptions

No data.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-07-21T17:15:13.196Z

Reserved: 2026-05-19T19:22:45.729Z

Link: CVE-2026-47395

cve-icon Vulnrichment

Updated: 2026-07-21T17:09:44.385Z

cve-icon NVD

No data.

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses
  • CWE-200

    Exposure of Sensitive Information to an Unauthorized Actor