GrafanaGhost Vulnerability Allows Data Theft via AI Injection

GrafanaGhost is a critical vulnerability in Grafana’s AI components that uses indirect prompt injection and protocol-relative URL bypasses to exfiltrate data...

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories

Large language models LLMs are increasingly embedded in open-source software OSS ecosystems, creating complex interactions among natural language prompts, probabilistic model outputs, and execution-capable components. However, it remains unclear whether traditional vulnerability disclosure...

@mobilenext/mobile-mcp: Arbitrary Android Intent Execution via mobile_open_url

Summary The mobileopenurl tool in mobile-mcp passes user-supplied URLs directly to Android's intent system without any scheme validation, allowing execution of arbitrary Android intents, including USSD codes, phone calls, SMS messages, and content provider access. Details The vulnerable code pass...

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness against Large Language Models

Prompt injection has emerged as a critical vulnerability in large language model LLM deployments, yet existing research is heavily weighted toward defenses. The attack side -- specifically, which injection strategies are most effective and why -- remains insufficiently studied.We address this gap...

PT-2026-30323

Name of the Vulnerable Software and Affected Versions Mobile Next versions prior to 0.0.50 Description The mobile open url tool in Mobile Next passes user-supplied URLs directly to Android's intent system without scheme validation, potentially allowing execution of arbitrary Android intents,...

Automating Cloud Security and Forensics through a Secure-By-Design Generative AI Framework

As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models LLMs have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic...

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem, analyzing 17,022 skills sampled from 170,226 on SkillsMP usi...

AgentWatcher: A Rule-Based Prompt Injection Monitor

Large language models LLMs and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: 1 their effectiveness degrades significantly as context length increases, and 2 they lack...

PraisonAI: Shell Injection in run_python() via Unescaped $() Substitution

Summary runpython in praisonai constructs a shell command string by interpolating user-controlled code into python3 -c "" and passing it to subprocess.run..., shell=True. The escaping logic only handles \ and ", leaving $ and backtick substitutions unescaped, allowing arbitrary OS command executi...

GHSA-5474-4W2J-MQ4C Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories

The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's...

CVE-2026-4399

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-34451 Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories

Claude SDK for TypeScript provides access to the Claude API from server-side TypeScript or JavaScript applications. From version 0.79.0 to before version 0.81.0, the local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did no...

EUVD-2026-17410

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

EUVD-2026-17357

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

CVE-2026-4399

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

CVE-2026-30308

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

CVE-2026-4399 Multiple vulnerabilities in 1millionbot Millie chatbot

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

CVE-2026-4399

The CVE-2026-4399 entry describes a prompt injection vulnerability in the 1millionbot Millie chatbot. The issue arises when a user bypasses chat restrictions via Boolean prompt injection, causing the model to execute an injected instruction after an affirmative ('true') response. Consequences sta...