AgentProv
← All incidents
2026-04-08 · 2026-Q2

PraisonAI Template Injection in Agent Tool Definitions

PrimaryL5ConfigSecondaryL2Instruction
Fixable:
Yes, vendor patch
Vendor response:
Patched
In the wild:
No
Actor:
Attacker

Target

PraisonAI (multi-agent teams framework, PyPI) prior to v4.5.115

Impact

Arbitrary code execution via template expressions injected into agent.start() input processed by create_agent_centric_tools()

Root Cause

Unescaped user input passed directly to template-rendering tools such as acp_create_file

View this entry in the catalog