Show HN: Argus, an open source security platform against agentic attacks
thomasunise · hn · 2026-10-25
Argus is an open-source security platform (GitHub: thomasunise/argus) designed to protect against agentic attacks, launched on HN. As agents gain tool execution and autonomy, prompt injection and tool-abuse risks grow, and dedicated guardrail infrastructure like this is emerging as its own security niche.
More from Safety
- User warns: before linking your bank to ChatGPT Finances, turn off model training — NickSlayr · 2026-10-25
- Good Will Hunting meme mocks 'ban open models' takes fresh off Dario's blog — HankYeomans · 2026-10-25
- FBI Probes Ex-OpenAI Engineer for Allegedly Stealing Secrets for Saudi Arabia — Polymarket · 2026-10-25
- Big Money Fueled Tech Advocacy to Deflect AI Cyber and CBRN Risk Concerns — AaronBergman18 · 2026-10-25
- Video: Your AI model could be hiding a backdoor — RelevantEmergency707 · 2026-10-25
- AI cyber defense worked: Team Defense found and patched bugs first — kuza55 · 2026-10-25