Vulnerability Description
PraisonAI (pip package praisonaiagents) before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.output_file path. A repository-controlled config file can set output_file to an absolute or '..' traversal path; when the developer subsequently calls agent.start() without explicitly passing an output parameter, PraisonAI writes the agent response to that path (creating parent directories as needed), allowing an untrusted checked-out project to overwrite files outside the project root with the privileges of the user running PraisonAI.
CVSS Score
MEDIUM
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/commit/3aa9cbc2bd49c23a32be0a89a5e620
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qjw5-xwrp-xw
- https://www.vulncheck.com/advisories/praisonai-before-path-traversal-via-config-
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qjw5-xwrp-xw
FAQ
What is CVE-2026-60089?
CVE-2026-60089 is a vulnerability with a CVSS score of 5.5 (MEDIUM). PraisonAI (pip package praisonaiagents) before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.out...
How severe is CVE-2026-60089?
CVE-2026-60089 has been rated MEDIUM with a CVSS base score of 5.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-60089?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.