CVE-2026-63443 Coder: Workspace agent API insecure redirect handling allowed cross-agent file read and write

Coder allows organizations to provision remote development environments via Terraform. Prior to 2.29.19, 2.32.9, 2.33.10, and 2.34.4, agentConn.apiClient follows redirects while its custom transport accepts the host from the redirected request URL when the port is the workspace agent HTTP API por...

PYSEC-2026-3516 PraisonAI: Unauthenticated Local File Inclusion via agent_file path in PraisonAI Jobs API

Summary An unauthenticated attacker can read arbitrary files on the server by supplying an absolute filesystem path in the agentfile field of the Jobs API. The field has no path validation, no allowlist, and no authentication is required to submit jobs. Details The agentfile field in...

PT-2026-64120

Summary An unauthenticated attacker can read arbitrary files on the server by supplying an absolute filesystem path in the agent file field of the Jobs API. The field has no path validation, no allowlist, and no authentication is required to submit jobs. Details The agent file field in...

CVE-2026-14687 666ghj BettaFish InsightEngine search-result Deduplication agent.py _deduplicate_results partial string comparison

A vulnerability was determined in 666ghj BettaFish up to 1.2.1. Impacted is the function deduplicateresults of the file InsightEngine/agent.py of the component InsightEngine search-result Deduplication. Executing a manipulation can lead to partial string comparison. The attack can be launched...

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...

PraisonAI: Unauthenticated Local File Inclusion via agent_file path in PraisonAI Jobs API

Summary An unauthenticated attacker can read arbitrary files on the server by supplying an absolute filesystem path in the agentfile field of the Jobs API. The field has no path validation, no allowlist, and no authentication is required to submit jobs. Details The agentfile field in...

Directory Traversal

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...

PT-2026-61773

Name of the Vulnerable Software and Affected Versions PraisonAI affected versions not specified Description An unauthenticated attacker can read arbitrary files on the server by providing an absolute filesystem path in the agent file field of the Jobs API. The system lacks path validation and an...

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...

GHSA-XQ8W-9JVX-GM3V hermes-agent has an Injection issue

A vulnerability was identified in NousResearch hermes-agent up to 0.12.0. Affected by this vulnerability is the function compresscontext of the file runagent.py. The manipulation leads to injection. It is possible to initiate the attack remotely. The exploit is publicly available and might be use...

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 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-2026-33232

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-2026-6663 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,...