Skip to content
OpenAdvisories
High · 8.8 CVE-2026-39891 EUVD-2026-20639GHSA-hwg5-x759-7wjgPYSEC-2026-2917

PraisonAI has a Template Injection in Agent Tool Definitions

Published Apr 8, 2026 · Updated Apr 9, 2026 · Assigned by GitHub_M

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.

Affected products

VendorProductAffectedFixed
MervinPraison PraisonAI < 4.5.115 —

Affected packages

EcosystemPackageAffectedFixedRecord
PyPI praisonai < 4.5.115 4.5.115 GHSA-hwg5-x759-7wjg

References