CVE-2026-61437 · Symaro Security Advisory

Description

PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praisonai-agents/praisonaiagents/workflows/workflows.py). When a workflow step uses a string output_pydantic reference, the framework locates and imports a sibling tools.py from the workflow file's directory via importlib exec_module without sandboxing, ignoring the PRAISONAI_ALLOW_*_TOOLS environment variables. An attacker who controls a workflow file and its sibling tools.py can execute arbitrary Python code with the workflow runner's privileges when the workflow is executed via WorkflowManager or after load_yaml.

Severity (CVSS)

Base score	8.5
Severity	High
Version	CVSS 4.0
Vector	CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Provided by	CNA

Weaknesses

CWE-693 — Protection Mechanism Failure

Affected products

Vendor	Product	Versions
MervinPraison	PraisonAI	0 to <1.6.78; 1.6.78

References

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4gfv-wg42-7jw5 (vendor-advisory)
https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-tools-py (third-party-advisory)

Authoritative sources

This page is a snapshot. For the latest enrichment and updates, view the record on CVE.org or the NVD.

Generated from the official CVE List on 11 Jul 2026 07:02 UTC.