Sofia_ Humanbound

Building Humanbound. An open-source adversarial testing engine, SDK, and CLI for AI agents. Join me in the issues https://github.com/humanbound

Greece Joined on Nov 8, 2022 https://Humanbound.ai

Sofia_ Humanbound for Humanbound

Sep 4

Promptfoo + Humanbound

#ai #security #opensource

3 min read

Want to connect with Sofia_ Humanbound?

Create an account to connect with Sofia_ Humanbound. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Sofia_ Humanbound for Humanbound

Sep 3

When Your Scraping Agent Becomes the Leak

#ai #security #opensource #agents

3 min read

Sofia_ Humanbound for Humanbound

Aug 31

Claude Code's Auto Mode just got broken, four days after Anthropic said prompt injection was basically solved

#security #ai #promptinjection

3 min read

Sofia_ Humanbound for Humanbound

Aug 28

Okta's Agent SSO Kills Static API Keys for AI Agents. It Doesn't Kill the Governance Problem.

#okta #aiagentsecurity #security #ai

5 min read

Sofia_ Humanbound for Humanbound

Aug 21

Agentic AI Security This Week: A Saturated Benchmark, 11 Framework CVEs, and 15 Competitors Who Finally Agree on Something

#agenticai #security #promptengineering #llm

5 min read

Sofia_ Humanbound for Humanbound

Aug 19

The Taiwan Attack: When an AI Agent Swarm Ran a Government Hack With No One Watching

#agenticai #aisecurity #cyberwarfare #redteam

3 min read

Sofia_ Humanbound for Humanbound

Aug 18

When the model that finds the bug is the same model that could exploit it

#ai #security #llm

6 min read

Sofia_ Humanbound for Humanbound

Aug 7

We're building a community library of agent attack scenarios, mapped to OWASP.

#ai #security #agents #owasp

2 min read

Sofia_ Humanbound for Humanbound

Aug 7

The approval prompt was never the control. Black Hat just admitted it.

#security #ai #agenticai #mcp

5 min read

Sofia_ Humanbound for Humanbound

Aug 4

Trust Boundary Report, Issue 02: The Month Agentic AI Stopped Being a Thought Experiment

#llm #agentic #ai #security

5 min read

Sofia_ Humanbound for Humanbound

Jul 29

Building a Public Backlog of AI Agent Failures: What's the Worst Thing Your Tests Didn't Catch?

#discuss #agents #promptengineering #ai

2 min read

Sofia_ Humanbound for Humanbound

Jul 28

AI Security Means Two Different Things. Mythos Made That Visible.

#ai #agents #security #opensource

7 min read

Sofia_ Humanbound for Humanbound

Jul 24

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

#ai #promptengineering #opensource #agents

2 min read

Sofia_ Humanbound for Humanbound

Jul 24

You're Still Alt-Tabbing to a Security Tool

#ai #mcp #agents #guardrails

6 min read

Sofia_ Humanbound for Humanbound

Jul 23

We put adversarial agent testing directly in Claude Code and Cursor

#ai #security #opensource #devtools

3 min read

Sofia_ Humanbound for Humanbound

Jul 22

Beyond Moderation: Why LLM Systems Need a Policy Layer

#llm #ai #agents #security

5 min read

Sofia_ Humanbound for Humanbound

Jul 21

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

#agents #security #ai #agentskills

8 min read

Sofia_ Humanbound for Humanbound

Jul 20

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

#ai #agents

6 min read

Sofia_ Humanbound for Humanbound

Jul 15

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

#ai #security #opensource #agents

1 min read

Sofia_ Humanbound for Developer Nation

Apr 19 '23

Taking a Proactive, Governance-Based Approach to API Security

6 min read

Sofia_ Humanbound for Developer Nation

Feb 8 '23

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

1 min read

DEV Community

Sofia_ Humanbound

Badges

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Three Year Club

Two Year Club

Writing Debut

One Year Club

Organizations

Developer Nation

Humanbound

Promptfoo + Humanbound

Want to connect with Sofia_ Humanbound?

When Your Scraping Agent Becomes the Leak

Claude Code's Auto Mode just got broken, four days after Anthropic said prompt injection was basically solved

Okta's Agent SSO Kills Static API Keys for AI Agents. It Doesn't Kill the Governance Problem.

Agentic AI Security This Week: A Saturated Benchmark, 11 Framework CVEs, and 15 Competitors Who Finally Agree on Something

The Taiwan Attack: When an AI Agent Swarm Ran a Government Hack With No One Watching

When the model that finds the bug is the same model that could exploit it

We're building a community library of agent attack scenarios, mapped to OWASP.

The approval prompt was never the control. Black Hat just admitted it.

Trust Boundary Report, Issue 02: The Month Agentic AI Stopped Being a Thought Experiment

Building a Public Backlog of AI Agent Failures: What's the Worst Thing Your Tests Didn't Catch?

AI Security Means Two Different Things. Mythos Made That Visible.

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

You're Still Alt-Tabbing to a Security Tool

We put adversarial agent testing directly in Claude Code and Cursor

Beyond Moderation: Why LLM Systems Need a Policy Layer

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

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

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

Taking a Proactive, Governance-Based Approach to API Security

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