# CVE-2026-47395: PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

> Attacker-controlled prompt text triggers automatic URL fetching, allowing access to internal loopback resources and injecting data into model context.

- **Severity:** Medium 5.5 (`CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Local or same network only
- **Victim action needed:** A user has to click or open something
- **Fix available:** Yes
- **Published:** 21 Jul 2026
- **Updated:** 21 Jul 2026
- **Also known as:** GHSA-5cxw-77wg-jrf3, PYSEC-2026-2903, PYSEC-2026-2942

## What is CVE-2026-47395?

CVE-2026-47395 is a medium-severity server-side request forgery vulnerability in MervinPraison PraisonAI, published on 21 Jul 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.

### 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.

Weakness: CWE-200 (Exposure of Sensitive Information to an Unauthorized Actor)

## Which versions are affected by CVE-2026-47395?

6 open source packages ship an affected version, including praisonaiagents, PraisonAI and praisonai.


| Package | Ecosystem | Affected | Fixed in |
| --- | --- | --- | --- |
| `praisonaiagents` | PyPI | All versions | 1.6.40 |
| `praisonaiagents` | PyPI | All versions | 1.6.40 |
| `praisonaiagents` | PyPI | All versions | 1.6.40 |
| `PraisonAI` | PyPI | All versions | 4.6.40 |
| `praisonai` | PyPI | All versions | 4.6.40 |
| `praisonai` | PyPI | All versions | 4.6.40 |

## How do I fix CVE-2026-47395?

Upgrade praisonaiagents to 1.6.40 or later.

## Is CVE-2026-47395 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-47395 exists.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-47395 and fix it if it is affected.

What it is: CVE-2026-47395 is a medium-severity server-side request forgery vulnerability in MervinPraison PraisonAI, published on 21 Jul 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-47395 exists.

Affected packages and fixed versions:
- praisonaiagents (PyPI): affected all versions; fixed in 1.6.40
- praisonaiagents (PyPI): affected all versions; fixed in 1.6.40
- praisonaiagents (PyPI): affected all versions; fixed in 1.6.40
- PraisonAI (PyPI): affected all versions; fixed in 4.6.40
- praisonai (PyPI): affected all versions; fixed in 4.6.40
- praisonai (PyPI): affected all versions; fixed in 4.6.40

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-47395/ (Markdown: https://insights.sbomify.com/CVE-2026-47395/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-47395
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-47395
- OSV: https://osv.dev/vulnerability/CVE-2026-47395

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-47395/
Summaries are generated and may contain mistakes; the official description above is the record.