Lucene search
+L

3 matches found

OSV
OSV
added 2026/06/18 2:27 p.m.9 views

GHSA-29W3-P9W9-WC47 PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

9.1CVSS5.9AI score
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/04/10 7:23 p.m.7 views

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

Summary readskillfile in skilltools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skillpath parameter. Unlike filetools.readfile which enforces workspace boundary confinement, and unlike runskillscript which requires critical-level approval, readskillfile has...

7.5CVSS5.9AI score0.00234EPSS
SaveExploits1References3Affected Software1
CVE
CVE
added 2026/04/09 9:21 p.m.15 views

CVE-2026-40117

CVE-2026-40117 concerns PraisonAIAgents, a multi-agent system. Before version 1.5.128, read_skill_file() in skill_tools.py allowed reading arbitrary filesystem files by accepting an unrestricted skill_path, lacking both workspace confinement and an approval gate. This enables potential data exfil...

7.5CVSS6AI score0.00234EPSS
SaveExploits1References1Affected Software1
Rows per page
Query Builder