Lucene search
K

41 matches found

RedhatCVE
RedhatCVE
added 2026/06/05 7:17 p.m.5 views

CVE-2026-33232

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

7.5CVSS5.4AI score0.00071EPSS
Exploits0References1
CVE
CVE
added 2026/06/01 3:45 a.m.18 views

CVE-2026-10221

CVE-2026-10221 affects NousResearch Hermes-agent up to version 0.12.0. The vulnerability is in the _compress_context function of run_agent.py, where input manipulation leads to injection. It can be triggered remotely over the network, and a public exploit is available. The vendor was contacted bu...

7.5CVSS6.8AI score0.00061EPSS
Exploits0References5
NVD
NVD
added 2026/05/19 2:16 a.m.12 views

CVE-2026-33232

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

7.5CVSS0.00071EPSS
Exploits0References2
ATTACKERKB
ATTACKERKB
added 2026/05/19 12:35 a.m.7 views

CVE-2026-33232

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

7.5CVSS5.8AI score0.00071EPSS
Exploits0References3Affected Software1
CVE
CVE
added 2026/05/19 12:35 a.m.13 views

CVE-2026-33232

The CVE-2026-33232 flaw affects AutoGPT Platform (versions 0.4.2–0.6.51). The issue is an unauthenticated DoS caused by the download_agent_file endpoint creating persistent temporary files per request and failing to delete them after serving, enabling an unauthenticated attacker to repeatedly exh...

7.5CVSS5.8AI score0.00071EPSS
Exploits0References2
Cvelist
Cvelist
added 2026/05/19 12:35 a.m.38 views

CVE-2026-33232 AutoGPT: Unauthenticated DoS via Disk Space Exhaustion

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

7.5CVSS0.00071EPSS
Exploits0References2
Cvelist
Cvelist
added 2026/05/12 7:48 a.m.36 views

CVE-2026-6663 GWD Connect <= 2.9 - Unauthenticated Limited Code Execution via update_agent

The GWD Connect plugin for WordPress is vulnerable to missing authorization to limited code execution in all versions up to, and including, 2.9. This is due to the plugin's standalone agent endpoints gwd-backup.php and gwd-logs.php not verifying authentication when the API key has not been...

4.8CVSS0.00114EPSS
Exploits0References3
Vulnrichment
Vulnrichment
added 2026/05/06 4:15 p.m.4 views

CVE-2026-20172 Cisco Enterprise Chat and Email Lite Agent File Upload Vulnerability

A vulnerability in the Lite Agent feature of Cisco Enterprise Chat and Email ECE could allow an authenticated, remote attacker to conduct browser-based attacks. To exploit this vulnerability, the attacker must have valid credentials for a user account with at least the role of Agent. This...

4.3CVSS6AI score0.00024EPSS
Exploits0References1
Cvelist
Cvelist
added 2026/04/09 9:14 p.m.16 views

CVE-2026-40111 PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py. No sanitization is performed and shell...

9.3CVSS0.00035EPSS
Exploits1References1
NVD
NVD
added 2026/04/08 9:17 p.m.1 views

CVE-2026-39890

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags such as !!js/function and !!js/undefined. This allows an attacker to craft a malicious YAML file that, when parsed,...

9.8CVSS0.00555EPSS
Exploits0References1
Vulnrichment
Vulnrichment
added 2026/04/08 8:45 p.m.1 views

CVE-2026-39890 PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags such as !!js/function and !!js/undefined. This allows an attacker to craft a malicious YAML file that, when parsed,...

9.8CVSS6.6AI score0.00555EPSS
Exploits0References1
CVE
CVE
added 2026/02/25 11:33 p.m.8 views

CVE-2026-27967

CVE-2026-27967 affects Zed code editor before 0.225.9. A symlink escape in Agent file tools (read_file, edit_file) lets reading/writing files outside the project directory when a project contains external symlinks, bypassing workspace boundaries and privacy protections (file_scan_exclusions, priv...

7.1CVSS5.5AI score0.00009EPSS
Exploits1References1Affected Software1
OSV
OSV
added 2026/02/25 11:33 p.m.5 views

CVE-2026-27967 Symlink Escape in Agent File Tools

Zed, a code editor, has a symlink escape vulnerability in versions prior to 0.225.9 in Agent file tools readfile, editfile. It allows reading and writing files outside the project directory when a project contains symbolic links pointing to external paths. This bypasses the intended workspace...

7.1CVSS5.7AI score0.00009EPSS
Exploits1References3
Cvelist
Cvelist
added 2026/02/25 11:33 p.m.14 views

CVE-2026-27967 Symlink Escape in Agent File Tools

Zed, a code editor, has a symlink escape vulnerability in versions prior to 0.225.9 in Agent file tools readfile, editfile. It allows reading and writing files outside the project directory when a project contains symbolic links pointing to external paths. This bypasses the intended workspace...

7.1CVSS0.00009EPSS
Exploits1References1
Vulnrichment
Vulnrichment
added 2026/02/25 11:33 p.m.4 views

CVE-2026-27967 Symlink Escape in Agent File Tools

Zed, a code editor, has a symlink escape vulnerability in versions prior to 0.225.9 in Agent file tools readfile, editfile. It allows reading and writing files outside the project directory when a project contains symbolic links pointing to external paths. This bypasses the intended workspace...

7.1CVSS6AI score0.00009EPSS
Exploits1References1
Positive Technologies
Positive Technologies
added 2026/02/25 12:0 a.m.2 views

PT-2026-22049

Name of the Vulnerable Software and Affected Versions Zed versions prior to 0.225.9 Description A symlink escape issue exists in Zed, a code editor, within the Agent file tools read file, edit file. This allows reading and writing files outside the project directory when the project contains...

7.1CVSS6AI score0.00009EPSS
Exploits1References7
RedhatCVE
RedhatCVE
added 2026/01/09 10:40 a.m.6 views

CVE-2022-35412

Digital Guardian Agent 7.7.4.0042 allows an administrator who ordinarily does not have a supported way to uninstall the product to disable some of the agent functionality and then exfiltrate files to an external USB device...

5.1CVSS6.8AI score0.00064EPSS
Exploits0References1
RedhatCVE
RedhatCVE
added 2026/01/09 8:49 a.m.3 views

CVE-2025-69220

LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior of arbitrary agents by uploading new files to t...

7.1CVSS6.8AI score0.00051EPSS
Exploits1References1
OSV
OSV
added 2026/01/07 8:49 p.m.3 views

CVE-2025-69220 LibreChat has Insufficient Access Control for Agent Files

LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior of arbitrary agents by uploading new files to t...

7.1CVSS6.7AI score0.00051EPSS
Exploits1References10
Vulnrichment
Vulnrichment
added 2026/01/07 8:49 p.m.2 views

CVE-2025-69220 LibreChat has Insufficient Access Control for Agent Files

LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior of arbitrary agents by uploading new files to t...

7.1CVSS6.4AI score0.00051EPSS
Exploits1References8
Rows per page
Query Builder