PYSEC-2026-289 Azure AI Language Authoring Elevation of Privilege Vulnerability can Lead to RCE

Deserialization of untrusted data in the Azure AI Language Conversations Authoring client library for Python allows an unauthorized attacker to execute code over a network...

PYSEC-2026-303 CAI find_file Agent Tool has Command Injection Vulnerability Through Argument Injection

Summary The CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with shell=True, allowing attackers to execute arbitrary commands on the host system. Vulnerable...

PYSEC-2026-412 Mesop Affected by Unauthenticated Remote Code Execution via Test Suite Route /exec-py

Summary An explicit web endpoint inside the ai/ testing module infrastructure directly ingests untrusted Python code strings unconditionally without authentication measures, yielding standard Unrestricted Remote Code Execution. Any individual capable of routing HTTP logic to this server block wil...

PYSEC-2026-446 Code execution in pandasai

GenerateSDFPipeline in syntheticdataframe in PandasAI aka pandas-ai through 1.5.17 allows attackers to trigger the generation of arbitrary Python code that is executed by SDFCodeExecutor. An attacker can create a dataframe that provides an English language specification of this Python code. NOTE:...

PYSEC-2026-349 H2O affected by a deserialization vulnerability

A deserialization vulnerability exists in h2oai/h2o-3 versions = 3.46.0.7, allowing attackers to read arbitrary system files and execute arbitrary code. The vulnerability arises from improper handling of JDBC connection parameters, which can be exploited by bypassing regular expression checks and...

PYSEC-2026-323 DB-GPT Absolute Path Traversal vulnerability

In eosphoros-ai/db-gpt version 0.6.0, the endpoint for uploading files is vulnerable to absolute path traversal. This vulnerability allows an attacker to upload arbitrary files to arbitrary locations on the target server. The issue arises because the filekey and docfile.filename parameters are...

EUVD-2026-40005

A flaw has been found in khoj-ai khoj up to 2.0.0-beta.28. This impacts an unknown function of the file src/khoj/routers/apichat.py of the component Conversation Sharing Handler. This manipulation of the argument conversation.agent causes incorrect authorization. Remote exploitation of the attack...

PT-2026-53303

Name of the Vulnerable Software and Affected Versions Devolutions PowerShell Universal version 2026.2.0 Description An information disclosure issue exists in the AI Agent job API. An authenticated user with AI Agent read access can obtain reusable, potentially higher-privileged authentication...

CVE-2026-13508

A flaw has been found in khoj-ai khoj up to 2.0.0-beta.28. This impacts an unknown function of the file src/khoj/routers/apichat.py of the component Conversation Sharing Handler. This manipulation of the argument conversation.agent causes incorrect authorization. Remote exploitation of the attack...

CVE-2026-13508 khoj-ai khoj Conversation Sharing api_chat.py authorization

A flaw has been found in khoj-ai khoj up to 2.0.0-beta.28. This impacts an unknown function of the file src/khoj/routers/apichat.py of the component Conversation Sharing Handler. This manipulation of the argument conversation.agent causes incorrect authorization. Remote exploitation of the attack...

CVE-2026-13508

A flaw has been found in khoj-ai khoj up to 2.0.0-beta.28. This impacts an unknown function of the file src/khoj/routers/apichat.py of the component Conversation Sharing Handler. This manipulation of the argument conversation.agent causes incorrect authorization. Remote exploitation of the attack...

CVE-2026-13508 khoj-ai khoj Conversation Sharing api_chat.py authorization

A flaw has been found in khoj-ai khoj up to 2.0.0-beta.28. This impacts an unknown function of the file src/khoj/routers/apichat.py of the component Conversation Sharing Handler. This manipulation of the argument conversation.agent causes incorrect authorization. Remote exploitation of the attack...

CVE-2026-13508

Affects khoj-ai khoj versions up to 2.0.0-beta.28; vulnerable component is the Conversation Sharing Handler in src/khoj/routers/api_chat.py, where manipulation of conversation.agent leads to incorrect authorization. The issue enables remote exploitation (exploit published) with attack vector over...

CVE-2026-13493

A flaw has been found in AIDC-AI ComfyUI-Copilot up to 2.0.28. This issue affects some unknown processing of the file backend/controller/conversationapi.py of the component Workflow Checkpoint Restore Handler. Executing a manipulation can lead to improper control of resource identifiers. The atta...

cyber-ai-agent

╔══════════════════════════════════════╗ ║ CYBER-OMNI...

PT-2026-53164

Name of the Vulnerable Software and Affected Versions khoj-ai khoj versions prior to 2.0.0-beta.29 Description A flaw in the Conversation Sharing Handler component within the file src/khoj/routers/api chat.py allows for incorrect authorization. This occurs through the manipulation of the...

EUVD-2026-37512

pydantic-ai: SSRF blocklist bypass via IPv4-compatible, SIIT/IVI, and local NAT64 IPv6 addresses incomplete fix of CVE-2026-46678...

GHSA-CG7W-RG45-PC59 pydantic-ai: SSRF blocklist bypass via IPv4-compatible, SIIT/IVI, and local NAT64 IPv6 addresses (incomplete fix of CVE-2026-46678)

Summary When an application using Pydantic AI opts a URL into forcedownload='allow-local' which disables the default block on private/internal IPs and runs on a network that routes the affected IPv6 transition forms NAT64- or ISATAP-configured networks, the cloud-metadata blocklist could be...

CVE-2025-32394 AutoGPT: There is a DoS vulnerability in AITextSummarizerBlock

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the...

EUVD-2026-39790

Docling simplifies document processing by parsing diverse formats and providing integrations with the generative AI ecosystem. From 2.45.0 until 2.91.0, the METS-GBS backend's XML parsing and the input document format detection lacked security controls. An attacker could craft malicious METS-GBS...