Vulnerability Description
PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, read_skill_file() in skill_tools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skill_path parameter. Unlike file_tools.read_file which enforces workspace boundary confinement, and unlike run_skill_script which requires critical-level approval, read_skill_file has neither protection. An agent influenced by prompt injection can exfiltrate sensitive files without triggering any approval prompt. This vulnerability is fixed in 1.5.128.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Praison | Praisonaiagents | < 1.5.128 |
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-grrg-5cg9-58ExploitVendor Advisory
FAQ
What is CVE-2026-40117?
CVE-2026-40117 is a vulnerability with a CVSS score of 6.2 (MEDIUM). PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, read_skill_file() in skill_tools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skill_path paramete...
How severe is CVE-2026-40117?
CVE-2026-40117 has been rated MEDIUM with a CVSS base score of 6.2/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-40117?
Check the references section above for vendor advisories and patch information. Affected products include: Praison Praisonaiagents.