Vulnerability · Published Jul 21, 2026 · Assigned by GitHub_M
CVE-2026-47395PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
Medium 5.5
In plain English
A medium-severity information exposure in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 8% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonai | 4.6.40 | GHSA-5cxw-77wg-jrf3 |
| PyPI | praisonai | 4.6.40 | PYSEC-2026-2903 |
| PyPI | praisonaiagents | 1.6.40 | GHSA-5cxw-77wg-jrf3 |
| PyPI | praisonaiagents | 1.6.40 | PYSEC-2026-2942 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | < 4.6.40 |
| MervinPraison | praisonaiagents | < 1.6.40 |
Weakness: CWE-200 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N