PT-2026-29087

A vulnerability was detected in raine consult-llm-mcp up to 2.5.3. Affected by this vulnerability is the function child process.execSync of the file src/server.ts. The manipulation of the argument git diff.base ref/git diff.files results in os command injection. The attack is only possible with...

GHSA-JJP7-G2JW-WH3J Open WebUI's process_files_batch() endpoint missing ownership check, allows unauthorized file overwrite

Summary Any authenticated user can overwrite any file's content by ID through the POST /api/v1/retrieval/process/files/batch endpoint. The endpoint performs no ownership check, so a regular user with read access to a shared knowledge base can obtain file UUIDs via GET /api/v1/knowledge/id/files a...

EUVD-2026-16478

vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out...

Detecting Protracted Vulnerabilities in Open Source Projects

Timely resolution and disclosure of vulnerabilities are essential for maintaining the security of open-source software. However, many vulnerabilities remain unreported, unpatched, or undisclosed for extended periods, exposing users to prolonged security threats. While various vulnerability...

CVE-2026-32247

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

An AI gateway designed to steal your data

A significant proportion of cyberincidents are linked to supply chain attacks, and this proportion is constantly growing. Over the past year, we have seen a wide variety of methods used in such attacks, ranging from creation of malicious but seemingly legitimate open-source libraries or delayed...

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

The emergence of Large Language Model-enhanced Search Engines LLMSEs has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summarization. While these systems demonstrate improved efficiency over traditional search engines, their security implication...

Guidance for detecting, investigating, and defending against the Trivy supply chain compromise

In this article 1. Analyzing the Trivy supply chain compromise 2. Detection and investigation 3. Mitigation and protection guidance 4. Advanced hunting queries 5. References 6. Learn more On March 19, 2026, Trivy, Aqua Security’s widely used open-source vulnerability scanner, was reported to have...

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Modern agentic systems allow Large Language Model LLM agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control flows as ephemeral, one-off sessions, overlooking the persisten...

CVE-2026-32628 AnythingLLM has SQL Injection in Built-in SQL Agent Plugin via Unsanitized table_name Parameter

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, a SQL injection vulnerability in the built-in SQL Agent plugin allows any user who can invoke the agent to execute arbitrary SQL commands on connected...

CVE-2026-32626 AnythingLLM has a Streaming Phase XSS to RCE via LLM Response Injection

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, AnythingLLM Desktop contains a Streaming Phase XSS vulnerability in the chat rendering pipeline that escalates to Remote Code Execution on the host OS...

Improper Neutralization of Special Elements in Data Query Logic

Overview graphiti-core is an A temporal graph building library Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Data Query Logic via the SearchFilters.nodelabels process. An attacker can execute arbitrary Cypher queries within the privileges of th...

nah Claude Code Tool

Claude Code's permission system is allow-or-deny per tool, but that doesn't really scale. Deleting some files is fine sometimes. And git checkout is sometimes catastrophic. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool’s errand. What's...

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents

Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool, enabling exploitable source-to-sink dataflows that only...

Malicious Package

Overview llm-oracle is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package authorship...

Malicious code in llm-oracle (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 98fdc3b2f8d6e1b4bb0e26b6f7f12227b5759900fb7c859b6b13093b1a159bf9 The package llm-oracle was found to contain malicious code. Source: ghsa-malware 94a20da2ad0a043d47545889257036cffa168646e3083c39007db16c692dc419 Any...

MAL-2026-1331 Malicious code in llm-oracle (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 98fdc3b2f8d6e1b4bb0e26b6f7f12227b5759900fb7c859b6b13093b1a159bf9 The package llm-oracle was found to contain malicious code. Source: ghsa-malware 94a20da2ad0a043d47545889257036cffa168646e3083c39007db16c692dc419 Any...

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

The rapid adoption of large language models LLMs in financial services introduces new operational, regulatory, and security risks. Yet most red-teaming benchmarks remain domain-agnostic and fail to capture failure modes specific to regulated BFSI settings, where harmful behavior can be elicited...

CVE-2026-27826

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to version 0.17.0, an unauthenticated attacker who can reach the mcp-atlassian HTTP endpoint can force the server process to make outbound HTTP requests to an arbitrary attacker-controlled URL b...

CVE-2025-12345

A security vulnerability has been detected in LLM-Claw 0.1.0/0.1.1/0.1.1a/0.1.1a-p1. The affected element is the function agentdeployinit of the file /agents/deploy/initiate.c of the component Agent Deployment. Such manipulation leads to buffer overflow. It is possible to launch the attack...