Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| MervinPraison / PraisonAI | affected 0 before 1.6.78; unaffected 1.6.78 |
CWE
CWE-693
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4gfv-wg42-7jw5
- https://www.vulncheck.com/advisories/praisonai-before-remote-code-execution-via-tools-py
ADP enrichment
No English description supplied.