Viewing profile — manuelnd
manuelnd
HN member- Joined
- Thu, Jan 29, 2026, 11:23 PM UTC
- HN karma
- 2
- Public activity
- 6 items
- HN profile
- View on Hacker News ↗
About manuelnd
No profile information was provided.
Recent public activity
-
story
We audited both MCP SDKs – three classes of boundary-crossing vulnerabilities
MCP (Model Context Protocol) has 77k+ stars and is becoming the standard way AI agents connect to tools. We audited both official SDKs (TypeScript and Python) at the source code le…
-
story
How to Red Team Your AI Agent in 48 Hours – A Practical Methodology
We published the methodology we use for AI red team assessments. 48 hours, 4 phases, 6 attack priority areas. This isn't theoretical — it's the framework we run against production …
-
story
The OWASP LLM Top: A Practical Attack Guide (with 122 real attack techniques)
Last week I shared our open-source taxonomy of 122 AI attack vectors. A lot of the discussion was about how the OWASP LLM Top 10 gives you categories but not specifics. So we wrote…
-
story
Show HN: Open-source taxonomy of 122 AI/LLM attack vectors
I've been doing AI red teaming for the past year and kept running into the same problem: there's no comprehensive catalog of how AI systems actually get broken. So I built one. 122…
-
comment
Comment #46822324
[dead]
-
comment
Comment #46822291
The sandbox opt-in default is the main gotcha though. Would be better if it defaulted to sandboxed with an explicit --no-sandbox flag for those who understand the risk