Skip to content
OpenAdvisories
Medium · 6.2 CVE-2026-40117 EUVD-2026-21164GHSA-grrg-5cg9-58pfPYSEC-2026-2949

PraisonAIAgents Affected by Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval Gate

Published Apr 9, 2026 · Updated Apr 10, 2026 · Assigned by GitHub_M

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.

Affected products

VendorProductAffectedFixed
MervinPraison PraisonAIAgents < 1.5.128 —

Affected packages

EcosystemPackageAffectedFixedRecord
PyPI praisonaiagents < 1.5.128 1.5.128 GHSA-grrg-5cg9-58pf

References