Resk
PulseAugur coverage of Resk — every cluster mentioning Resk across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
LLM access control and routing papers highlight cost, security, and reliability risks
Two research papers and several blog posts explore the complexities of managing Large Language Model (LLM) access and usage. One paper, EquiRouter, introduces a new routing method to optimize costs by intelligently sele…
-
New LLM Firewall 'Resk' Launched to Prevent Prompt Injection Attacks
A new open-source LLM firewall called Resk has been developed to protect services like Qonto from prompt injection attacks and sensitive data exposure. Resk acts as a proxy between an application and an LLM provider, of…
-
AI agent security: Controlling LLM actions at the tool boundary
AI agent security focuses on controlling the actions of LLM systems, not just their output. Best practices emphasize implementing access controls at the tool boundary rather than relying solely on prompt-level defenses.…
-
AI agent security hinges on tool boundary controls, not prompts
Securing AI agents requires implementing access controls at the tool boundary, rather than relying on the model's prompt for security. The recommended approach involves authenticating the caller, authorizing specific to…
-
LLMs tested on Godot coding; AI agent security guide released
A new benchmark from Flockbay tested several large language models on their ability to generate Godot Engine code, with Claude Opus 5.5, Claude Sonnet 5.5, and GPT-6.1 Sol all passing 15 out of 15 tasks. Claude Haiku 4.…
-
New open-source firewall Resk protects LLMs from prompt injection
A new open-source tool called Resk has been released to help protect AI applications, such as travel planning assistants, from indirect prompt injection attacks. This firewall solution can be deployed in front of any Op…
-
AI security, auditability, and new frontier models explored · 4 sources tracked
Developers are exploring new methods to enhance AI security and auditability. One approach involves using ReskPoints to log, mask, and audit LLM-powered support agents, preventing Personally Identifiable Information (PI…
-
AI Agents: Secure Tool Access and Monitoring Best Practices Detailed
This series of articles from dev.to discusses best practices for implementing access controls and monitoring for AI agents. The core message emphasizes that security should be enforced at the tool invocation boundary, r…
-
New Firewall Tool Protects Customer Support LLMs from PII Leaks
A new open-source tool called Resk has been developed to act as a firewall for customer-support AI assistants, preventing the exfiltration of Personally Identifiable Information (PII). The tool, built with FastAPI and R…
-
Resk launches self-hosted LLM firewall for enhanced security
Resk has released a self-hosted LLM firewall designed to enhance security for OpenAI-compatible providers. This firewall, built with FastAPI and React, addresses risks such as prompt injection, data leakage, and unautho…
-
ReskSecure library blocks LLM jailbreaks at logits level
Resk has released reskSecure, a Python library designed to prevent prompt injection and jailbreak attacks in production LLM systems. Unlike traditional methods that filter output text, reskSecure operates at the logits …
-
New open-source tool blocks LLM jailbreaks at GPU speed
A new open-source tool called resk-logits has been developed to enhance LLM safety by intercepting and suppressing harmful outputs at the logit level during token generation. This GPU-accelerated Aho-Corasick engine can…