# CVE-2026-55522: PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code

> Attackers can execute arbitrary Python code by including malicious local recipes, bypassing security gates in PraisonAI libraries.

- **Severity:** High 7.8 (`CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H`)
- **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:** 5 Aug 2026
- **Updated:** 6 Aug 2026
- **Also known as:** GHSA-hxmv-c4g6-5fqc, PYSEC-2026-3891, PYSEC-2026-3903

## What is CVE-2026-55522?

CVE-2026-55522 is a high-severity code injection vulnerability in MervinPraison PraisonAI, published on 5 Aug 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. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow "include" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe's tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.

Weakness: CWE-94 (Improper Control of Generation of Code), CWE-829 (Inclusion of Functionality from Untrusted Control Sphere), CWE-426 (Untrusted Search Path)

## Which versions are affected by CVE-2026-55522?

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


| Package | Ecosystem | Affected | Fixed in |
| --- | --- | --- | --- |
| `praisonaiagents` | PyPI | From 0.12.12 | 1.6.58 |
| `praisonaiagents` | PyPI | From 0.12.12 | 1.6.58 |
| `praisonaiagents` | PyPI | From 0.12.12 | 1.6.58 |
| `PraisonAI` | PyPI | From 3.9.26 | 4.6.58 |
| `praisonai` | PyPI | From 3.9.26 | 4.6.58 |
| `praisonai` | PyPI | From 3.9.26 | 4.6.58 |

## How do I fix CVE-2026-55522?

Upgrade praisonaiagents to 1.6.58 or later.

## Is CVE-2026-55522 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-55522 exists.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-55522 and fix it if it is affected.

What it is: CVE-2026-55522 is a high-severity code injection vulnerability in MervinPraison PraisonAI, published on 5 Aug 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-2026-55522 exists.

Affected packages and fixed versions:
- praisonaiagents (PyPI): affected from 0.12.12; fixed in 1.6.58
- praisonaiagents (PyPI): affected from 0.12.12; fixed in 1.6.58
- praisonaiagents (PyPI): affected from 0.12.12; fixed in 1.6.58
- PraisonAI (PyPI): affected from 3.9.26; fixed in 4.6.58
- praisonai (PyPI): affected from 3.9.26; fixed in 4.6.58
- praisonai (PyPI): affected from 3.9.26; fixed in 4.6.58

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-2026-55522/ (Markdown: https://insights.sbomify.com/CVE-2026-55522/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-55522
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-55522
- OSV: https://osv.dev/vulnerability/CVE-2026-55522

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-55522/
Summaries are generated and may contain mistakes; the official description above is the record.