llm security
30 articles about llm security in AI news
LLMs Default to Zod Schemas, Breaking MCPFusion Security Contracts
LLMs default to raw Zod schemas, bypassing MCPFusion's defineModel() and risking data leaks. The Developer Prover enforces MVA architecture via rejection.
3 MCP Gateway Security Gaps LiteLLM's Audit Found (And How to Fix Them in
LiteLLM's audit revealed 3 MCP gateway gaps: fail-open resolver, unpinned servers, opt-in least-privilege. Fix them in Claude Code with version pinning and allowed_tools.
Never Let the LLM Write the Joins
This article details a two-phase text-to-SQL pipeline: Phase A deterministically plans (intent, entity resolution, joins, RBAC) and Phase B executes with bounded LLM calls. The subject graph caches entity mappings lazily, and security is enforced before the model sees any schema.
Research Paper Proposes Security Framework for Autonomous AI Agents in Commerce
A Systematization of Knowledge (SoK) paper analyzes the emerging threat landscape for autonomous LLM agents conducting commerce. It identifies 12 attack vectors across five dimensions and proposes a layered defense architecture. This is a foundational security analysis for a nascent but high-stakes technology.
How to Use an MCP Gateway to Centralize Security and Cost Control for
An MCP gateway like Bifrost centralizes security, observability, and cost management for Claude Code by routing all MCP tool calls through a single policy-enforced endpoint.
LLM agents fail nonlinearly as tasks lengthen, 27-paper synthesis finds
27-paper synthesis finds LLM agent failures compound nonlinearly with task length. Six failure clusters identified across 19 benchmarks.
FreeLLMAPI Aggregates 1.7B Free Tokens/Month Across 11 Providers
FreeLLMAPI aggregates 11 free LLM providers into one endpoint, offering 1.7B tokens/month with automatic fallover. Reduces friction for side projects but faces provider tolerance risks.
OpenAI, Broadcom Unveil Jalapeño ASIC for LLM Inference
OpenAI and Broadcom unveiled Jalapeño, a custom ASIC for LLM inference, targeting volume deployment by late 2026. No performance metrics were disclosed.
New 474-Game Benchmark Reveals LLMs Collapse on Counterfactual Reasoning
New 474-game benchmark reveals LLMs fail on counterfactual reasoning, with larger drops than contextual perturbations. Highlights metacognitive gaps in agentic AI.
Claude Security Public Beta Launches in Claude Code on Web
Anthropic launched Claude Security in public beta for Claude Code on web, letting developers validate and fix vulnerabilities without leaving the editor.
VoteGCL: A Novel LLM-Augmented Framework to Combat Data Sparsity in
A new paper introduces VoteGCL, a framework that uses few-shot LLM prompting and majority voting to create high-confidence synthetic data for graph-based recommendation systems. It integrates this data via graph contrastive learning to improve accuracy and mitigate bias, outperforming existing baselines.
AI Agent Security Startup Emerges Amid Enterprise Rush, Per VC Tweet
A VC's tweet highlights a critical gap in enterprise AI agent adoption: security. This signals a market opportunity, with a new startup reportedly emerging to address it.
LLMs Can De-Anonymize Users from Public Data, Study Warns
Large Language Models can now piece together a person's identity from their public online trail, rendering pseudonyms ineffective. This raises significant privacy and security concerns for internet users.
Akshay Pachaar Inverts LLM Agent Architecture with 'Harness' Design
AI engineer Akshay Pachaar outlined a novel 'harness' architecture for LLM agents that externalizes intelligence into memory, skills, and protocols. He is building a minimal, didactic open-source implementation of this design.
HUOZIIME: A Research Framework for On-Device LLM-Powered Input Methods
A new research paper introduces HUOZIIME, a personalized on-device input method powered by a lightweight LLM. It uses a hierarchical memory mechanism to capture user-specific input history, enabling privacy-preserving, real-time text generation tailored to individual writing styles.
llm-anthropic 0.25 Adds Opus 4.7 with xhigh Thinking Effort — Here's How
Update to llm-anthropic 0.25 to access Claude Opus 4.7 with xhigh thinking_effort for tackling your most challenging code problems.
Multi-User LLM Agents Struggle: Gemini 3 Pro Scores 85.6% on Muses-Bench
A new benchmark reveals LLMs struggle with multi-user scenarios where agents face conflicting instructions. Gemini 3 Pro leads but only achieves 85.6% average, with privacy-utility tradeoffs proving particularly difficult.
Karpathy's LLM Wiki Hits 5k Stars, Gains Memory Lifecycle Extension
Andrej Karpathy's LLM Wiki repository gained 5,000 GitHub stars in two days. A developer has now extended it with memory lifecycle features, addressing a noted gap.
MCP Security Crisis: 43% of Servers Vulnerable, 341 Malicious Skills Found
Security audits of the Model Context Protocol (MCP) ecosystem reveal 43% of servers are vulnerable to command execution, while 341 malicious skills were found on marketplaces, exposing systemic security flaws in agentic AI. The findings highlight a growing attack surface as AI agents become more autonomous.
Keygraph Launches Shannon AI to Automate Web App Security Testing
Keygraph has launched 'Shannon,' an AI agent that autonomously hacks web applications to find security flaws. This positions AI as an offensive security tool for proactive defense.
A Practical Guide to Fine-Tuning Open-Source LLMs for AI Agents
This Portuguese-language Medium article is Part 2 of a series on LLM engineering for AI agents. It provides a hands-on guide to fine-tuning an open-source model, building on a foundation of clean data and established baselines from Part 1.
Paper: LLMs Fail 'Safe' Tests When Prompted to Role-Play as Unethical Characters
A new paper reveals that large language models (LLMs) considered 'safe' on standard benchmarks will readily generate harmful content when prompted to role-play as unethical characters. This exposes a critical blind spot in current AI safety evaluation methods.
GameMatch AI Proposes LLM-Powered Identity Layer for Semantic Search in Recommendations
A new Medium article introduces GameMatch AI, a system that uses an LLM to create a user identity layer from descriptive paragraphs, aiming to move beyond click-based recommendations. The concept suggests a shift towards understanding user intent and identity for more personalized discovery.
Audit Your MCP Servers in 10 Seconds with This Free Security Score API
A new free API gives Claude Code users a Lighthouse-style security score for any MCP server, revealing that 60% of scanned packages have vulnerabilities.
MemoryCD: New Benchmark Tests LLM Agents on Real-World, Lifelong User Memory for Personalization
Researchers introduce MemoryCD, the first large-scale benchmark for evaluating LLM agents' long-context memory using real Amazon user data across 12 domains. It reveals current methods are far from satisfactory for lifelong personalization.
Open-Source Multi-Agent LLM System for Complex Software Engineering Tasks Released by Academic Consortium
A consortium of researchers from Stony Brook, CMU, Yale, UBC, and Fudan University has open-sourced a multi-agent LLM system specifically architected for complex software engineering. The release aims to provide a collaborative, modular framework for tackling tasks beyond single-agent capabilities.
Human Security Report: AI Agent Traffic Surges 8000%, Bots Now Outpace Humans on Internet
A new report from cybersecurity firm Human Security finds automated traffic grew 8x faster than human activity in 2025, with AI agent traffic exploding by nearly 8,000%. This marks a tipping point where bots now dominate internet traffic.
A Technical Guide to Prompt and Context Engineering for LLM Applications
A Korean-language Medium article explores the fundamentals of prompt engineering and context engineering, positioning them as critical for defining an LLM's role and output. It serves as a foundational primer for practitioners building reliable AI applications.
Tessera Launches Open-Source Framework for 32 OWASP AI Security Tests, Benchmarks GPT-4o, Claude, Gemini, Llama 3
Tessera introduces the first open-source framework to run all 32 OWASP AI security tests against any model with one CLI command. It provides benchmark results for GPT-4o, Claude, Gemini, Llama 3, and Mistral across 21 model-specific security tests.
PyPI Quarantines LiteLLM Package After Supply Chain Attack Compromises AI Integration Tool
The Python Package Index (PyPI) has quarantined the LiteLLM package after a supply chain attack distributed a malicious update. The action prevents automatic installation of the compromised version via pip.