# PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage

Advisory record · `GHSA-j7qx-p75m-wp7g`

- **Identifiers:** `GHSA-j7qx-p75m-wp7g` · `CVE-2026-56834` · `PYSEC-2026-3514`
- **State:** Confirmed
- **Severity:** CVSS 7.5 High
- **Critical:** No
- **Weakness (CWE):** [CWE-22](https://cwe.mitre.org/data/definitions/22.html) · [CWE-200](https://cwe.mitre.org/data/definitions/200.html)
- **Tags:** [Path traversal](https://agentprime.io/advisories/tag/path-traversal.md) · [Information disclosure](https://agentprime.io/advisories/tag/info-disclosure.md)
- **Published:** 18 Jun 2026
- **Updated:** 23 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 18 Jun 2026, 13:52 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `praisonai` (PyPI): affected `>=3.8.1, <4.6.59`; fixed in `4.6.59`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> GHSA-j7qx-p75m-wp7g affects the PyPI package praisonai from 3.8.1 up to but not including 4.6.59, and the fix is in 4.6.59. The artifact helper tools (artifact_head, artifact_tail, artifact_grep, artifact_chunk) read any host file path they are given without checking it is inside the artifact storage directory. An attacker who can influence the tool arguments, such as through a prompt to an exposed agent, can read files the PraisonAI process can access, including credentials and .env files. Upgrade to praisonai 4.6.59 or later.

Written 5 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 7.5 High, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0037, the 31st percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:41 UTC: First seen by agentprime
- 31 Oct 2026, 14:41 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-j7qx-p75m-wp7g)

## Sources

- [GitHub Advisory Database: GHSA-j7qx-p75m-wp7g](https://github.com/advisories/GHSA-j7qx-p75m-wp7g)
- [OSV: GHSA-j7qx-p75m-wp7g](https://osv.dev/vulnerability/GHSA-j7qx-p75m-wp7g)
- <https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j7qx-p75m-wp7g>
- <https://github.com/MervinPraison/PraisonAI>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-j7qx-p75m-wp7g>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-j7qx-p75m-wp7g/>. Everything for agents: <https://agentprime.io/llms.txt>.
