CVE-2026-61437
PraisonAI before 1.6.78 Remote Code Execution via tools.py
- State
- Published
- Severity
- 8.5 High
- Published
- Jul 10, 2026
- Updated
- Jul 14, 2026
- Reserved
- Jul 9, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 8.5 High | 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 | VulnCheck |
| 3.1 | 7.8 High | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | VulnCheck |
Weaknesses
- CWE-693 Protection Mechanism Failure
Affected Products
| Product | Versions |
|---|---|
PraisonAIMervinPraison |
|
References
- GitHub Security Advisory (GHSA-4gfv-wg42-7jw5)vendor-advisory
- VulnCheck Advisory: PraisonAI before 1.6.78 Remote Code Execution via tools.pythird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.