8743 matches found
Leveraging Trustworthy AI for Automotive Security in Multi-Domain Operations: Towards a Responsive Human-AI Multi-Domain Task Force for Cyber Social Security
Multi-Domain Operations MDOs emphasize cross-domain defense against complex and synergistic threats, with civilian infrastructures like smart cities and Connected Autonomous Vehicles CAVs emerging as primary targets. As dual-use assets, CAVs are vulnerable to Multi-Surface Threats MSTs,...
PT-2025-30619 · Robocode · Robocode
Name of the Vulnerable Software and Affected Versions: Roo Code versions 3.23.18 and below Description: Roo Code, an AI-powered autonomous coding agent, does not validate line breaks in its command input. This bypasses the allow-list mechanism due to a lack of parsing or validation logic,...
CVE-2025-51458
SQL Injection in editorsqlrun and queryex in eosphoros-ai DB-GPT 0.7.0 allows remote attackers to execute arbitrary SQL statements via crafted input passed to the /v1/editor/sql/run or /v1/editor/chart/run endpoints, interacting with apieditorv1.editorsqlrun, editorchartrun, and...
CVE-2025-51459
File Upload vulnerability in agent.hub.controller.refreshplugins in eosphoros-ai DB-GPT 0.7.0 allows remote attackers to execute arbitrary code via a malicious plugin ZIP file uploaded to the /v1/personal/agent/upload endpoint, interacting with pluginhub.sanitizefilename and pluginsutil.scanplugi...
Flowable’s Summer 2025 Update Introduces Groundbreaking Agentic AI Capabilities
Flowable’s 2025.1 update brings powerful Agentic AI features to automate workflows, boost efficiency, and scale intelligent business operations...
CVE-2025-51482
Remote Code Execution in letta.server.restapi.routers.v1.tools.runtoolfromsource in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions...
CVE-2025-51859
Stored Cross-Site Scripting XSS vulnerability in Chaindesk thru 2025-05-26 in its agent chat component. An attacker can achieve arbitrary client-side script execution by crafting an AI agent whose system prompt instructs the underlying Large Language Model LLM to embed malicious script payloads...
CVE-2025-51867
Insecure Direct Object Reference IDOR vulnerability in Deepfiction AI deepfiction.ai thru June 3, 2025, allowing attackers to chat with the LLM using other users' credits via sensitive information gained by the /browse/stories endpoint...
Microsoft Sentinel data lake: Unify signals, cut costs, and power agentic AI
You can’t protect what you can’t see. Security operations teams have long been faced with the challenge of managing massive, fast-growing datasets, and the cost of scaling traditional data management tools to handle these data volumes has become unsustainable. We’re evolving our industry-leading...
‘Car crash victim’ calls mother for help and $15K bail money. But it’s an AI voice scam
A woman in Florida was tricked into giving thousands of dollars to a scammer after her daughter's voice was AI-cloned and used in a scam. Sharon Brightwell says she received a call from someone who sounded just like her daughter. The woman on the other end was sobbing and crying, telling her mom...
WordPress AI Tools <= 4.0.7 - Arbitrary Content Deletion Vulnerability
Arbitrary Content Deletion Vulnerability discovered by theviper17 in WordPress Plugin AI Tools versions = 4.0.7...
CVE-2025-51865
Ai2 playground web service playground.allenai.org LLM chat through 2025-06-03 is vulnerable to Insecure Direct Object Reference IDOR, allowing attackers to gain sensitvie information via enumerating thread keys in the URL...
PT-2025-30428 · Chaindesk · Chaindesk
Name of the Vulnerable Software and Affected Versions: Chaindesk versions through 2025-05-26 Description: A stored Cross-Site Scripting XSS vulnerability exists in the agent chat component. An attacker can execute arbitrary client-side scripts by creating an AI agent with a system prompt designed...
CVE-2025-51867
CVE-2025-51867 affects Deepfiction AI and is an Insecure Direct Object Reference (IDOR) vulnerability exploiting the /browse/stories endpoint to let an attacker chat with the LLM using other users’ credits. Root cause: improper access controls exposing sensitive information tied to user credits. ...
CVE-2025-51458
SQL Injection in editorsqlrun and queryex in eosphoros-ai DB-GPT 0.7.0 allows remote attackers to execute arbitrary SQL statements via crafted input passed to the /v1/editor/sql/run or /v1/editor/chart/run endpoints, interacting with apieditorv1.editorsqlrun, editorchartrun, and...
CVE-2025-51859
Chaindesk is affected by a stored XSS in the agent chat component through crafted system prompts that instruct the LLM to inject malicious payloads (e.g., SVG-based XSS) into chat responses. This can cause arbitrary client-side script execution in victims’ browsers, enabling theft of sensitive da...
CVE-2025-51860
Stored Cross-Site Scripting XSS in TelegAI telegai.com 2025-05-26 in its chat component and character container component. An attacker can achieve arbitrary client-side script execution by crafting an AI Character with SVG XSS payloads in either description, greeting, example dialog, or system...
CVE-2025-51458
DB-GPT 0.7.0 is affected by a SQL injection in the editor_sql_run and query_ex paths. The vulnerability allows remote attackers to craft input to /v1/editor/sql/run and /v1/editor/chart/run that interacts with api_editor_v1.editor_sql_run, editor_chart_run, and datasource.rdbms.base.query_ex to e...
CVE-2025-51459
File Upload vulnerability in agent.hub.controller.refreshplugins in eosphoros-ai DB-GPT 0.7.0 allows remote attackers to execute arbitrary code via a malicious plugin ZIP file uploaded to the /v1/personal/agent/upload endpoint, interacting with pluginhub.sanitizefilename and pluginsutil.scanplugi...
CVE-2025-51867
Insecure Direct Object Reference IDOR vulnerability in Deepfiction AI deepfiction.ai thru June 3, 2025, allowing attackers to chat with the LLM using other users' credits via sensitive information gained by the /browse/stories endpoint...