Top all-time · #14626
Manifold
Company blog · manifold.security/blogsecurityai
Manifold is the company blog at manifold.security, writing about security and ai. Since 2026, 5 different Hacker News readers have linked it 8 times, most often “GitSpawn: Untrusted repos can execute code via AI coding agents”. No feed was found, so read it on the site itself.
Coding agents are on your endpoints. Do you know what they're doing? Manifold gives security teams runtime visibility into autonomous AI agents.
Most-linked posts?
- GitSpawn: Untrusted repos can execute code via AI coding agents4 people · 4 mentions · first linked 2026-09-01
What Hacker News says?
Submitted Ask a model if code is malicious and it reaches for its morals as a story · 15 points
HN discussionSubmitted GitSpawn: Untrusted repos can execute code via AI coding agents as a story · 9 points
HN discussionSubmitted GitSpawn: Flaw Lets Untrusted Repos Run Code in Claude Code, Codex, Cursor, Grok as a story · 5 points
HN discussionSubmitted GitSpawn: A Single Flaw Lets Untrusted Repos Run Code in Claude Code, and Others as a story · 3 points
HN discussionSubmitted AI agents have few qualms with log tampering as a story · 2 points
HN discussionSubmitted A Single Flaw Lets Untrusted Repos Run Code in Claude Code, Codex, Cursor, Grok as a story · 2 points
HN discussionSubmitted 30 ClawHub Skills Are Quietly Recruiting Your AI Agent into a Crypto Swarm as a story · 2 points
HN discussionSubmitted ClawHub's 23 plugins squat the official @openclaw and @clawhub scopes as a story · 1 points
HN discussion