Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Large Language Model LLM-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain...

CVE-2026-15077 Improper Neutralization of Input Used for LLM Prompting in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.3 and 19.2 before 19.2.1 that under certain conditions could have allowed an authenticated user to access information from unauthorized projects due to improper neutralization of untrusted content processed b...

Gitlab -- vulnerabilities

Gitlab reports: Sensitive Information Exposure issue in Workhorse impacts GitLab CE/EE Mass Assignment issue in Pipeline Schedule API impacts GitLab CE/EE Denial of Service issue in Merge Request Discussions impacts GitLab CE/EE Race Condition issue in merge request approval rules impacts GitLab ...

Security Bulletin: IBM Watson Speech Services Cartridge is vulnerable to incomplete validation in LangChain [CVE-2026-40087]

Summary IBM Watson Speech Services Cartridge is vulnerable to incomplete validation in LangChain, due to flaws in the f-string prompt-template. CVE-2026-40087. LangChain is used in our speech runtimes. This vulnerability has been addressed. Please read the details for remediation below...

CVE-2026-17534

Kimi Code @moonshot-ai/kimi-code before 0.27.0 implements FetchURL SSRF hardening as a static hostname and IP-literal denylist in assertSafeFetchTarget, without resolving DNS or re-validating hosts after HTTP redirects. An attacker who can influence a FetchURL call for example via prompt injectio...

CVE-2026-17534 Kimi Code FetchURL SSRF protection bypass via DNS-resolving hostnames and redirects

Kimi Code @moonshot-ai/kimi-code before 0.27.0 implements FetchURL SSRF hardening as a static hostname and IP-literal denylist in assertSafeFetchTarget, without resolving DNS or re-validating hosts after HTTP redirects. An attacker who can influence a FetchURL call for example via prompt injectio...

CVE-2026-17534: Server-Side Request Forgery (SSRF)

Kimi Code @moonshot-ai/kimi-code before 0.27.0 implements FetchURL SSRF hardening as a static hostname and IP-literal denylist in assertSafeFetchTarget, without resolving DNS or re-validating hosts after HTTP redirects. An attacker who can influence a FetchURL call for example via prompt injectio...

DarkPrompt

DarkPrompt !CIhttps://github.com/jason-allen-oneal/DarkPr...

PT-2026-64811

Name of the Vulnerable Software and Affected Versions NoteGen versions prior to 0.32.0 Description Cross-site scripting occurs when AI chat responses are rendered using markdown-it with the html:true configuration and injected into the DOM via dangerouslySetInnerHTML in the chat-preview component...

Denial Of Service (DoS)

vLLM is vulnerable to Denial of Service DoS. The vulnerability is due to improper handling of prompt embedding payloads for models using M-RoPE, which allows an authenticated attacker to trigger an assertion failure and crash the entire server by sending a crafted /v1/completions request...

GHSA-FWJX-9P69-H25H Oh My Posh: Terminal escape sequence injection via unsanitized prompt segment data

Summary Oh My Posh renders dynamic, potentially attacker-controlled strings the current directory name, Git commit metadata, environment variable values, command output into the prompt without neutralizing raw terminal control characters. An attacker who controls one of these values can inject...

Oh My Posh: Terminal escape sequence injection via unsanitized prompt segment data

Summary Oh My Posh renders dynamic, potentially attacker-controlled strings the current directory name, Git commit metadata, environment variable values, command output into the prompt without neutralizing raw terminal control characters. An attacker who controls one of these values can inject...

EUVD-2026-40117

Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution...

GHSA-7835-87Q9-RGVV Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution

Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite file...

CVE-2026-66027

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

CVE-2026-66027 Suna < 0.9.102 Broken Access Control via Message Queue API

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

EUVD-2026-48641

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

CVE-2026-66027 Suna < 0.9.102 Broken Access Control via Message Queue API

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

CVE-2026-66027

Suna before 0.9.102 contains a broken access control vulnerability in the message queue API that allows authenticated attackers to access and manipulate queue resources belonging to other users by exploiting missing ownership and account isolation checks. Attackers can read pending prompt queues ...

CVE-2026-66004

BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the downloadpolyhavenasset method that allows attackers to write arbitrary files by injecting traversal sequences in API response include keys. Attackers performing MITM attacks or prompt injection can supply malicious...