Lucene search
K

6 matches found

RedhatCVE
RedhatCVE
added 2026/04/13 7:23 p.m.1 views

CVE-2026-40149

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, a...

7.9CVSS5.8AI score0.00015EPSS
Exploits1References1
Github Security Blog
Github Security Blog
added 2026/04/10 7:24 p.m.3 views

PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

Summary The gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, an attacker can cause the ExecApprovalManager to...

7.9CVSS6AI score0.00015EPSS
Exploits1References4Affected Software1
EUVD
EUVD
added 2026/04/10 7:24 p.m.0 views

EUVD-2026-21168

PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls...

7.9CVSS5.8AI score0.00015EPSS
Exploits1References3
ATTACKERKB
ATTACKERKB
added 2026/04/09 9:23 p.m.1 views

CVE-2026-40149

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, a...

7.9CVSS5.9AI score0.00015EPSS
Exploits1References2Affected Software1
Vulnrichment
Vulnrichment
added 2026/04/09 9:23 p.m.0 views

CVE-2026-40149 PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, a...

7.9CVSS5.8AI score0.00015EPSS
Exploits1References1
Positive Technologies
Positive Technologies
added 2026/04/09 12:0 a.m.0 views

PT-2026-31788

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth token is configured the default. By adding dangerous tool names e.g., shell exec, file write to the allowlist...

7.9CVSS5.9AI score0.00015EPSS
Exploits1References4
Rows per page
Query Builder