← 최신 프로덕트

Beating GPT5.5-xhigh for Coding agent security with SLMs and IRM

Research and evidence behind Harden Agentic Integrity Foundation (AIF): local cybersecurity-focused LLMs that evaluate coding-agent tool calls before execution. Coding agents craft arbitrary code so securing them is more complicated than red-teaming.

harden.run 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Akmon

    github.com

    a Rust AI coding agent for regulated engineering

    Hacker News5점

  2. A CTF challenge that let's you attack an LLM-based agent

    news.ycombinator.com

    The challenge is designed to test the robustness of LLM-based agent systems, showcasing how an attacker can extract sensitive information from the system.

    Hacker News5점

  3. Strix

    usestrix.com

    AI Cybersecurity Agent, securing your vibe coding

    Hacker News102점

  4. Benchmark your team's AI coding security posture

    news.ycombinator.com

    We launched a free AI Coding Risk Assessment tool to help engineering teams and businesses benchmark the security and compliance posture of their AI coding workflows and policies against peers in the industry.

    Hacker News5점

  5. Implement-spec

    github.com

    a harness-agnostic spec-to-verified-PR agent skill

    Hacker News12점