22 matches found
Linux Distros Unpatched Vulnerability : CVE-2026-109561
The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because...
CVE-2026-109561
A flaw was found in goose. An authorization bypass vulnerability allows tools to run without required user confirmation even when manual approval mode is selected. This occurs because read-only tool annotations from previous sessions are not properly cleared when switching approval modes...
CVE-2026-109561
goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because persisted read-only annotations are never cleared by updategoosemode. After a session uses Smart Approval mode, prompt-injected calls to...
CVE-2026-109561
The goose tool (versions 1.28.0 before 1.44.0 ) is vulnerable to an authorization bypass in its permission handling. The root cause is that persisted read-only annotations are not cleared by the update_goose_mode function. This allows an attacker to use prompt injection to execute tools without u...
EUVD-2026-97884
goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because persisted read-only annotations are never cleared by updategoosemode. After a session uses Smart Approval mode, prompt-injected calls to...
CVE-2026-109561 goose from 1.28.0 before 1.44.0 Manual Approval Bypass via Read-Only Tool Annotations
goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because persisted read-only annotations are never cleared by updategoosemode. After a session uses Smart Approval mode, prompt-injected calls to...
CVE-2026-109561
goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because persisted read-only annotations are never cleared by updategoosemode. After a session uses Smart Approval mode, prompt-injected calls to...
CVE-2026-109561: Incorrect Authorization
goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because persisted read-only annotations are never cleared by updategoosemode. After a session uses Smart Approval mode, prompt-injected calls to...
PT-2026-110937
goose from 1.28.0 before 1.44.0 contains an authorization bypass vulnerability that allows tools to run without user approval in Manual Approval mode because persisted read-only annotations are never cleared by update goose mode. After a session uses Smart Approval mode, prompt-injected calls to...
EUVD-2026-37959
PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...
CVE-2026-56075
PrasionAI before 4.5.128 contains an arbitrary shell command execution vulnerability in which UI modules hardcode approval_mode to auto, overriding the PRAISON_APPROVAL_MODE environment variable. This allows authenticated attackers to instruct the LLM agent to run arbitrary commands via subproces...
CVE-2026-56075
PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...
CVE-2026-56075 PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override
PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...
CVE-2026-56075 PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override
PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...
Incorrect Authorization
Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...
GHSA-QWGJ-RRPJ-75XM PraisonAI: Hardcoded `approval_mode="auto"` in Chainlit UI Overrides Administrator Configuration, Enabling Unapproved Shell Command Execution
Summary The Chainlit UI modules chat.py and code.py hardcode config.approvalmode = "auto" after loading administrator configuration from the PRAISONAPPROVALMODE environment variable, silently overriding any "manual" or "scoped" approval setting. This defeats the human-in-the-loop approval gate fo...
PraisonAI: Hardcoded `approval_mode="auto"` in Chainlit UI Overrides Administrator Configuration, Enabling Unapproved Shell Command Execution
Summary The Chainlit UI modules chat.py and code.py hardcode config.approvalmode = "auto" after loading administrator configuration from the PRAISONAPPROVALMODE environment variable, silently overriding any "manual" or "scoped" approval setting. This defeats the human-in-the-loop approval gate fo...
PT-2026-33900
Summary The Chainlit UI modules chat.py and code.py hardcode config.approval mode = "auto" after loading administrator configuration from the PRAISON APPROVAL MODE environment variable, silently overriding any "manual" or "scoped" approval setting. This defeats the human-in-the-loop approval gate...
Incorrect Authorization
Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization in the exec approval mode on macOS node-hosts when basename-only allowlist entries are configured. An attacker can execute unauthorized local binaries by creating ...
Microsoft Windows: User Account Control: Admin Approval Mode for the Built-in Administrator account
This policy setting determines the behavior of Admin Approval Mode for the built-in administrator account. When the Admin Approval Mode is enabled, the local administrator account functions like a standard user account, but it has the ability to elevate privileges without logging on by using a...