DEV Community

Sofia Aliferi profile picture

Sofia Aliferi

Join me in the issues https://github.com/humanbound

Location Greece Joined Joined on  Personal website https://Humanbound.ai github website twitter website
A new paper argues that your prompt injection defence can't win.
sofaliferi profile

A new paper argues that your prompt injection defence can't win.

#ai #promptengineering #opensource #agents
1
Comments
2 min read
You're Still Alt-Tabbing to a Security Tool
sofaliferi profile

You're Still Alt-Tabbing to a Security Tool

#ai #mcp #agents #guardrails
2
Comments
6 min read
We put adversarial agent testing directly in Claude Code and Cursor
sofaliferi profile

We put adversarial agent testing directly in Claude Code and Cursor

#ai #security #opensource #devtools
4
Comments
3 min read
Beyond Moderation: Why LLM Systems Need a Policy Layer
sofaliferi profile

Beyond Moderation: Why LLM Systems Need a Policy Layer

#llm #ai #agents #security
1
Comments
5 min read
Why Your AI Agent's Biggest Vulnerability Isn't a Missing Firewall
sofaliferi profile

Why Your AI Agent's Biggest Vulnerability Isn't a Missing Firewall

#agents #security #ai #agentskills
2
Comments 2
8 min read
The Enforcement illusion: Why AI Agent Security Starts with Testing, Not Walls
sofaliferi profile

The Enforcement illusion: Why AI Agent Security Starts with Testing, Not Walls

#ai #agents
2
Comments 1
6 min read
AI agent evaluation is evolving. Here's what we're building.
sofaliferi profile

AI agent evaluation is evolving. Here's what we're building.

#ai #security #opensource #agents
4
Comments 1
1 min read
Taking a Proactive, Governance-Based Approach to API Security
sofaliferi profile

Taking a Proactive, Governance-Based Approach to API Security

4
Comments
6 min read
Pulse Report - Key Insights from the 23rd Edition of the Developer Nation Survey
sofaliferi profile

Pulse Report - Key Insights from the 23rd Edition of the Developer Nation Survey

1
Comments
1 min read
loading...