Home

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.

PUBLISHED Reserved 2026-04-09 | Published 2026-04-09 | Updated 2026-04-10 | Assigner GitHub_M




MEDIUM: 6.2CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Problem types

CWE-862: Missing Authorization

Product status

< 1.5.128
affected

References

github.com/...isonAI/security/advisories/GHSA-grrg-5cg9-58pf

cve.org (CVE-2026-40117)

nvd.nist.gov (CVE-2026-40117)

Download JSON