Hackernews posts about Entrust

1. The Deathray: A simple way for an untrusted site to freeze a Mac (auberon.xyz)
   273 points by auberonedu 7 days ago | 194 comments
2. GitSpawn: Untrusted repos can execute code via AI coding agents (www.manifold.security)
   9 points by fourfire 12 days ago | 3 comments
3. GitSpawn: Flaw Lets Untrusted Repos Run Code in Claude Code, Codex, Cursor, Grok (www.manifold.security)
   5 points by chillax 14 days ago | discuss
4. Jailbox: Network-Restricted, Hardened Linux VMs for AI Agents and Untrusted Code (karamatli.com)
   5 points by sparsesignal 21 days ago | discuss
5. GitSpawn: A Single Flaw Lets Untrusted Repos Run Code in Claude Code, and Others (www.manifold.security)
   3 points by 0xmagic0 16 days ago | 1 comments
6. A Single Flaw Lets Untrusted Repos Run Code in Claude Code, Codex, Cursor, Grok (www.manifold.security)
   2 points by axsharma 15 days ago | 7 comments
7. Another Slice of Swiss Cheese for Untrusted Monitoring (www.lesswrong.com)
   2 points by joozio 3 days ago | discuss
8. Ontologies catch untrustworthy LLM claims (antithetical-labs.com)
   2 points by aals777 14 days ago | discuss
9. Lind-project: Run untrusted POSIX applications, safely, in one process (lind-project.github.io)
   1 points by ryuuseijin 5 days ago | discuss
10. Show HN: Apollo Lunar Module landing simulation (gosandeep.com)
    50 points by gosandeep 8 days ago | 5 comments
11. Show HN: MCP app for Android, drive apps via AI (no root, PII redacted locally) (github.com)
    6 points by daniele_dll 29 days ago | 2 comments
12. Show HN: Hands-Rust MCP/CLI that sees the Windows desktop and clicks real Chrome
    5 points by ryan-b 25 days ago | 2 comments
13. Show HN: Gibson ADK and Zero Trust Runtime (www.zeroroot.ai)
    3 points by zerodayai 23 days ago | 1 comments
14. Show HN: Kaflow Search – A desktop tool for locally indexed Kafka message search (kaflow-search.whsoul-tools.com)
    2 points by whsoul about 20 hours ago | discuss
15. Show HN: Pragma Twice – A dystopian sci-fi themed programming game (www.bryanpg.com)
    2 points by umvi 7 days ago | discuss
16. Original Sony PlayStation 2 security chip 'broken wide open' after 26 years (www.tomshardware.com)
    275 points by rbanffy about 22 hours ago | 82 comments
17. Prompt Injection Through Tool Output Is Two Events (Your Screens Read One) (www.armosec.io)
    2 points by gmays 8 days ago | discuss
18. Sandbox Boundaries (cantelop.com)
    1 points by arsentjev 6 days ago | discuss
19. More questions about whether researchers can trust OpenAI with unpublished math (mathstodon.xyz)
    866 points by pred_ 7 days ago | 818 comments
20. AI Is Breaking This Thing We Call Trust (terriblesoftware.org)
    128 points by matheusml 7 days ago | 69 comments
21. Microsoft's latest update breaks domain trust, causing widespread login failures (www.neowin.net)
    8 points by speckx 1 day ago | discuss
22. Sam Altman says world 'right to be afraid' but 'should trust' AI firms (www.bbc.com)
    5 points by geox 1 day ago | 4 comments
23. Ask HN: What would make you trust an AI's assessment of your understanding?
    4 points by Aditya_0315 3 days ago | 3 comments
24. Why a Swift AI pause is unlikely: No one trusts AI companies (www.axios.com)
    4 points by 1vuio0pswjnm7 1 day ago | discuss
25. Overlord – a trust kernel for AI agents (github.com)
    3 points by b1tr0n1n about 7 hours ago | discuss
26. Intel TDX Remote Attestation Verifier Without Intel Trust Authority (zatona.dev)
    3 points by dzatona 1 day ago | discuss
27. Show HN: Prmptree – AI email agent with a trust dial, not an on/off switch (www.prmptree.com)
    3 points by doingmybest1 3 days ago | discuss
28. Open-1B: the first model you don't have to trust (www.gensyn.ai)
    2 points by modinfo about 12 hours ago | discuss
29. Ask HN: How many runs before you trust a coding agent's result?
    1 points by Marvin_RunAI about 7 hours ago | 1 comments
30. Measuring and Exploiting Implicit Trust in LLM Tool-Calling Pipelines (arxiv.org)
    1 points by sbulaev about 1 hour ago | discuss