PT-2026-55696

Name of the Vulnerable Software and Affected Versions NousResearch hermes-agent versions prior to 2026.4.31 Description A weakness in the HTTP API component allows a remote attacker to cause a denial of service. The issue exists within the AIAgent.run conversation function located in the run...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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,...

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,...

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...

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...

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...

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...

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...

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...

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...

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...