Hackernews posts about Codex Security

1. Claude, Codex, and Hermes installed unowned code inside corporate networks (arstechnica.com)
   7 points by toomuchtodo 24 days ago | 2 comments
2. Researchers escape OpenAI Codex sandbox to run commands on host (www.bleepingcomputer.com)
   1 points by Brajeshwar about 9 hours ago | discuss
3. Claude, Codex, and Hermes installed unowned code inside corporate networks (arstechnica.com)
   1 points by nreece 20 days ago | discuss
4. Ask HN: What is the proper way of preventing AI labs to use your private data
   1 points by ozgung 11 days ago | 1 comments
5. Tell HN: OpenAI keeps stealing my money
   11 points by dingdong2026 12 days ago | 4 comments
6. GitSpawn: Flaw Lets Untrusted Repos Run Code in Claude Code, Codex, Cursor, Grok (www.manifold.security)
   5 points by chillax 18 days ago | discuss
7. A Single Flaw Lets Untrusted Repos Run Code in Claude Code, Codex, Cursor, Grok (www.manifold.security)
   2 points by axsharma 19 days ago | 7 comments
8. Tell HN: Check your Claude settings, it may have silently enabled remote access
   7 points by cromka 16 days ago | 6 comments
9. Show HN: MaruCheck – Independent QA for AI-generated code (github.com)
   3 points by KidusMT 10 days ago | 2 comments
10. NPM extends recovery-code security holds to all accounts (github.blog)
    1 points by soheilpro 10 days ago | discuss
11. TimeCodeSecurity – Deterministic AST SAST and Auto-Remediation for Python
    3 points by AyushGaur 1 day ago | 1 comments
12. Ask HN: Experiences with Anthropic's Cyber Verification Program?
    3 points by zuInnp 3 days ago | discuss
13. Show HN: Verity.md quality gates, memory and cost control for Claude Code (verity.md)
    1 points by ARayOutOfBounds 18 days ago | discuss
14. Write security-sensitive code in Swift (www.youtube.com)
    1 points by pjmlp 7 days ago | discuss
15. How SaaS startup guys get first 100 customers first, make fkn $500k ARR fast?
    22 points by nandakishor_ml 8 days ago | 42 comments
16. Ask HN: How is AI actively a threat to humanity if it's only online?
    5 points by CM30 7 days ago | 14 comments
17. Safer-dependencies is a security layer for Claude Code that audits dependencies (github.com)
    1 points by zenomorph 27 days ago | discuss
18. Flock cameras are riddled with security vulnerabilities and hardcoded creds (micahflee.com)
    49 points by micahflee 4 days ago | 6 comments
19. VibeGuard – security linter for AI-generated code (github.com)
    8 points by obadafid 19 days ago | 1 comments
20. VibeGuard – security linter for AI-generated code (github.com)
    2 points by obadafid 22 days ago | discuss
21. Show HN: VibeGuard – security linter for AI-generated code (github.com)
    1 points by obadafid 22 days ago | 1 comments
22. Did Vibe Coders win? Is this our end?
    4 points by s_u_d_o 18 days ago | 6 comments
23. What AI code review misses: SSRF and more (zeroquarry.com)
    1 points by eskibars 20 days ago | 1 comments
24. Show HN: Security Cards – Reducing insecure AI-generated code by 72% (www.rewarelabs.com)
    4 points by hajipour 10 days ago | 2 comments
25. Show HN: Beating GPT5.5-xhigh for Coding agent security with SLMs and IRM (harden.run)
    9 points by se4u 24 days ago | 5 comments
26. GitSpawn: Untrusted repos can execute code via AI coding agents (www.manifold.security)
    9 points by fourfire 16 days ago | 3 comments
27. Show HN: I built a SaaS without knowing how to code – am I an idiot? (www.learnfrom.co)
    6 points by bel_hajo 26 days ago | 6 comments
28. GitSpawn: A Single Flaw Lets Untrusted Repos Run Code in Claude Code, and Others (www.manifold.security)
    3 points by 0xmagic0 19 days ago | 1 comments
29. Over 8,300 Gitea servers vulnerable to code execution attacks (www.bleepingcomputer.com)
    3 points by geoffbp 23 days ago | discuss
30. Over 8,300 Gitea servers vulnerable to code execution attacks (www.bleepingcomputer.com)
    3 points by speckx 23 days ago | discuss