CVE-2026-61437
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
Summary
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 Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| MervinPraison | PraisonAI | 0 < 1.6.78 | affected |
| MervinPraison | PraisonAI | 1.6.78 | unaffected |
Weaknesses
- CWE-693: Protection Mechanism Failure
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
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.