Manipulating AI Summarization Features

Microsoft is reporting: Companies are embedding hidden instructions in "Summarize with AI" buttons that, when clicked, attempt to inject persistence commands into an AI assistant's memory via URL prompt parameters…. These prompts instruct the AI to "remember Company as a trusted source" or...

CVE-2026-20064: NULL Pointer Dereference

A vulnerability in of Cisco Secure Firewall Threat Defense FTD Software could allow an authenticated, local attacker to cause the device to unexpectedly reload, causing a denial of service DoS condition. This vulnerability is due to improper validation of user-supplied input. An attacker with a...

GHSA-V6X2-2QVM-6GV8 OpenClaw reuses the gateway auth token in the owner ID prompt hashing fallback

Vulnerability OpenClaw reused gateway.auth.token and gateway.remote.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay=hash and commands.ownerDisplaySecret was unset. This created secret dual-use between gateway authentication and prompt metadata hashing...

Insufficiently Protected Credentials

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Insufficiently Protected Credentials due to the reuse of authentication tokens as a fallback secret in the owner ID prompt hashing process. An attacker can infer sensitive hash outputs by...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization through a mismatch in wrapper-depth parsing in system.run. An attacker can bypass approval gating by crafting nested transparent dispatch wrappers, allowing...

OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs

Summary In sandboxed runs, native prompt image auto-load did not honor tools.fs.workspaceOnly=true. This optional hardening setting is not enabled by default. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths for example /agent/secret.png and load...

GHSA-9F72-QCPW-2HXC OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs

Summary In sandboxed runs, native prompt image auto-load did not honor tools.fs.workspaceOnly=true. This optional hardening setting is not enabled by default. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths for example /agent/secret.png and load...

Exploit for Code Injection in Anthropic Claude_Code

CVE-PENDING: MCP Tool Confirmation Prompt Misrepresentation in...

AI Agents: The Next Wave Identity Dark Matter - Powerful, Invisible, and Unmanaged

The Rise of MCPs in the Enterprise The Model Context Protocol MCP is quickly becoming a practical way to push LLMs from “chat” into real work. By providing structured access to applications, APIs, and data, MCP enables prompt-driven AI agents that can retrieve information, take action, and automa...

Malicious code in web-prompt (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c25d3dc9dade58627dd5a799f9069218fc45fc00534c36c5ec6adcc972e18c5f The package web-prompt was found to contain malicious code. Source: ghsa-malware 1c2c7c89562fb0e8f3db62cdf48f299b872398a2ea68e0a2e0b503c3cd7bd54a Any...

MAL-2026-1184 Malicious code in web-prompt (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c25d3dc9dade58627dd5a799f9069218fc45fc00534c36c5ec6adcc972e18c5f The package web-prompt was found to contain malicious code. Source: ghsa-malware 1c2c7c89562fb0e8f3db62cdf48f299b872398a2ea68e0a2e0b503c3cd7bd54a Any...

PT-2026-25487

Vulnerability OpenClaw reused gateway.auth.token and gateway.remote.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay=hash and commands.ownerDisplaySecret was unset. This created secret dual-use between gateway authentication and prompt metadata hashing...

PT-2026-26746

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.22 Description The software reuses the gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset. This...

GHSA-4GC2-344Q-R2RW MS-Agent vulnerable to Command Injection

A Command Injection vulnerability in ModelScope's MS-Agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256 Command injection vulnerability in ModelScope's ms-agent

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256: Improper Neutralization of Special Elements used in a Command

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

OpenClaw Code Injection Vulnerability

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a code injection vulnerability. The vulnerability stems from the fact that channel metadata may be included in the model's system prompts when the Slack integration is enabled, increasing the attack...

MS-Agent does not properly sanitize commands sent to its shell tool, allowing for RCE

Overview A command injection vulnerability was identified in the MS-Agent framework that can be triggered through unsanitized prompt-derived input. An attacker can craft untrusted input introduced via a chat prompt or other external content sources, resulting in arbitrary command execution on the...