HIGH 7.8 GitHub
CVE-2026-61437
PraisonAI: Unsafe Dynamic Module Loading Leads to Arbitrary Code Execution via tools.py in AgentFlow
### Summary
An unsafe dynamic module loading vulnerability allows an attacker who can control a workflow file and a sibling `tools.py` to execute arbitrary Python code when the workflow is executed.
### Details
The vulnerability is located in the workflow structured output resolution logic.
File: src/praisonai-agents/praisonaiagents/workflows/workflows.py
Method: AgentFlow._resolve_pydantic_class
```python
if self.file_path:
workflow_dir = Path(self.file_path).parent
tools_path = wor
Affected Products
- pip/praisonaiagents <= 1.6.77
References
- https://github.com/advisories/GHSA-4gfv-wg42-7jw5
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4gfv-wg42-7jw5
- https://nvd.nist.gov/vuln/detail/CVE-2026-61437
- https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-tools-py
This high severity vulnerability with a CVSS score of 7.8 was published on 2026-10-08 via GitHub. Affected: pip/praisonaiagents <= 1.6.77.
vulnfeed aggregates 13827 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.