Viewing profile — AskCarX
AskCarX
HN member- Joined
- Sun, Mar 08, 2026, 6:58 PM UTC
- HN karma
- 3
- Public activity
- 27 items
- HN profile
- View on Hacker News ↗
About AskCarX
No profile information was provided.
Recent public activity
- story
-
comment
Comment #47638840
AgenticSearch is a search engine for AI agents. Not ranked by links. Ranked by cryptographic trust. Every result carries dual ECDSA P-256 signatures. Agents search for capabilities…
- story
-
comment
Comment #47585562
ATTP is a synchronous request-response protocol for AI agents calling web APIs. Runs over HTTP with mandatory ECDSA P-256 signing, agent identity passports, trust-gated access (L0-…
- story
-
comment
Comment #47553070
I built a deliberately vulnerable MCP (Model Context Protocol) server for security testing and scanner validation. 10 intentional vulnerabilities covering the OWASP MCP Top 10 -- a…
- story
- story
- story
- story
- story
- story
- story
-
story
Show HN: MCPS – Cryptographic identity and message signing for MCP agents
We scanned 39 agent frameworks against the OWASP Agentic AI Top 10. 13 FAIL, 17 WARN, 9 PASS. Open Interpreter scored 80/100 risk. AutoGPT 65. Even LangChain flagged WARN for promp…
- story
- story
- story
-
comment
Comment #47338151
Thanks for flagging the email issue -- DNS MX records are being configured now. In the meantime, reach us at contact@agentsign.dev (that one works) or raza.sharif@outlook.com direc…
- story
-
comment
Comment #47335787
This is interesting but the big question nobody's asking: how do you trust the agents NemoClaw deploys? Nvidia is solving agent deployment and orchestration. But once you have thou…
-
story
Show HN: AgentSign – Open-source zero trust engine for AI agents
Hi HN. This week Meta acquired Moltbook (agent social network), OpenAI acquired Promptfoo (agent testing), and Mandiant's founder raised $190M for Armadin. Agent infrastructure is …
-
comment
Comment #47335429
Hi there. The irony here is pretty clear -- Meta acquired an agent social network that went viral specifically because agents were posting fake content. The "always-on directory" a…
-
comment
Comment #47333999
Hi there — you're raising the right questions and these are exactly the attack vectors I built AgentSign to handle. It's not just signing. AgentSign has 5 subsystems (patent pendin…
-
comment
Comment #47325585
To add some context on why this matters now -- I audited the 12 most popular agent frameworks and found none of them have agent identity, cryptographic signing, or trust scoring: A…
-
comment
Comment #47325213
[dead]