Your Agent Is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt...

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...

Missing Authorization

Overview prompts.chat is a Developer toolkit for AI prompts - build, validate, parse, and connect to prompts.chat Affected versions of this package are vulnerable to Missing Authorization due to the missing isPrivate checks in API endpoints and page metadata generation. An attacker can access...

CVE-2026-22663 prompts.chat Authorization Bypass Information Disclosure

prompts.chat prior to commit 7b81836 contains multiple authorization bypass vulnerabilities due to missing isPrivate checks across API endpoints and page metadata generation that allow unauthorized users to access sensitive data associated with private prompts. Attackers can exploit these missing...

CVE-2026-22663 prompts.chat Authorization Bypass Information Disclosure

prompts.chat prior to commit 7b81836 contains multiple authorization bypass vulnerabilities due to missing isPrivate checks across API endpoints and page metadata generation that allow unauthorized users to access sensitive data associated with private prompts. Attackers can exploit these missing...

CVE-2026-22663 prompts.chat Authorization Bypass Information Disclosure

prompts.chat prior to commit 7b81836 contains multiple authorization bypass vulnerabilities due to missing isPrivate checks across API endpoints and page metadata generation that allow unauthorized users to access sensitive data associated with private prompts. Attackers can exploit these missing...

CVE-2026-22661

Prompts.chat is affected by a path-traversal vulnerability in skill file handling prior to commit 0f8d4c3. Attackers can craft ZIP archives with unsanitized filenames that include ../ path sequences, bypassing server-side filename validation, causing extraction to write files outside the intended...

CVE-2026-26927

Szafir SDK Web is a browser plug-in that can run SzafirHost application which download the necessary files when launched. In Szafir SDK Web it is possible to change the URL HTTP Origin of the application call location. An unauthenticated attacker can craft a website that is able to launch...

LangChain Core < 1.2.22 Path Traversal (GHSA-qh6h-p6c9-ff54)

The version of LangChain Core installed on the remote host is prior to 1.2.22. It is, therefore, affected by a path traversal vulnerability: - Multiple functions in langchaincore.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory...

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...

CVE-2026-26927

Szafir SDK Web is a browser plug-in that can run SzafirHost application which download the necessary files when launched. In Szafir SDK Web it is possible to change the URL HTTP Origin of the application call location. An unauthenticated attacker can craft a website that is able to launch...

PT-2026-29741

Szafir SDK Web is a browser plug-in that can run SzafirHost application which download the necessary files when launched. In Szafir SDK Web it is possible to change the URL HTTP Origin of the application call location. An unauthenticated attacker can craft a website that is able to launch...

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...