MAL-2026-5601 Malicious code in 0x2ai-multi-q (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e305b12731a6b73c8982935753b52febfa90626f5a75f6942ca154aa708594b6 Running npx 0x2ai-multi-q the package's documented invocation spawns claude --dangerously-skip-permissions and writes a .mcp.json into the user's...

Malicious code in 0x2ai-multi-q (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e305b12731a6b73c8982935753b52febfa90626f5a75f6942ca154aa708594b6 Running npx 0x2ai-multi-q the package's documented invocation spawns claude --dangerously-skip-permissions and writes a .mcp.json into the user's...

MAL-2026-5590 Malicious code in 0x2ai-demo3 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a36d5f023e4740169d1e1e7a56ebe32552cfdc4a05bf50ecc0b648ecea502c0d On npm install, scripts/postinstall.cjs copies the entire payload/ tree into process.env.INITCWD the directory the developer ran the install from usi...

MAL-2026-5594 Malicious code in 0x2ai-demo7x (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c7e956073a7db6057e4d42af462dba0299152ca992c113d74c715e90574d0efb On npm install, scripts/postinstall.cjs copies the package's payload/ tree into the installer's project root process.env.INITCWD, placing...

MAL-2026-5596 Malicious code in 0x2ai-demo8x (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f6d1ce2d7b8faa5bde122eb2bc6e0a79fec5f5720cfa7de0718a0c8948b344d6 On npm install, scripts/postinstall.cjs copies the package's payload/ tree into INITCWD the consumer's project root using fs.cpSync,...

Malicious code in 0x2ai-demo1 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fdc7c661d4867578d3dd920010bccc1e79fcae8753b5bf549f44ea8a45cde502 On npm install, scripts/postinstall.cjs runs fs.cpSyncpayload, cwd, recursive: true with cwd=process.env.INITCWD || process.cwd — recursively writing...

MAL-2026-5587 Malicious code in 0x2ai-demo1 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fdc7c661d4867578d3dd920010bccc1e79fcae8753b5bf549f44ea8a45cde502 On npm install, scripts/postinstall.cjs runs fs.cpSyncpayload, cwd, recursive: true with cwd=process.env.INITCWD || process.cwd — recursively writing...

Linux Distros Unpatched Vulnerability : CVE-2026-48107

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a...

CVE-2026-48107

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

CVE-2026-48107

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

DEBIAN-CVE-2026-48107

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

CVE-2026-48107

Russh (Rust SSH client/server) is affected in versions 0.37.0–0.60.x where the client’s keyboard-interactive auth path accepts an attacker-controlled prompt count via USERAUTH_INFO_REQUEST. The code uses the raw count directly in Vec::with_capacity(...) before verifying sufficient prompt data, en...

CVE-2026-48107 Russh: Unchecked keyboard-interactive prompt count in client auth path

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

CVE-2026-48107 Russh: Unchecked keyboard-interactive prompt count in client auth path

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

CVE-2026-48107 Russh: Unchecked keyboard-interactive prompt count in client auth path

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

CVE-2026-48107

Russh is a Rust SSH client & server library. From version 0.37.0 to before version 0.61.0, in the russh client keyboard-interactive authentication path, a malicious SSH server could send a USERAUTHINFOREQUEST with an attacker-controlled prompt count, and the client would use that raw count direct...

Compromise OpenClaw with Prompt Injections in Message Objects

Executive Summary As powerful personal AI assistants become increasingly widespread, their ability to access tools, files, and external services also makes them susceptible to prompt injection attacks, where malicious content can manipulate their behavior. This research evaluated OpenClaw against...

PT-2026-48545

Name of the Vulnerable Software and Affected Versions russh versions 0.37.0 through 0.60.2 Description In the keyboard-interactive authentication path of the client, a malicious SSH server can send a USERAUTH INFO REQUEST containing an attacker-controlled prompt count. The client uses this raw...

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models LLMs are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at...

Reconstructing AI activity in investigations

AI systems are now part of everyday work. Investigators need a consistent way to reconstruct what happened within them. Security teams are already investigating activity involving Microsoft 365 Copilot and Azure AI services—from prompt injection attempts to unexpected data access. Those signals a...