Security / Local AI Security
A blog post describing Annex, a local-AI security tool that encrypts selected files during agent sessions to keep sensitive data away from local AI tools. The post explains the threat model, encryption flow, and the stack used to build it.
The page clearly presents a real AI-adjacent product idea with enough visible detail for a directory listing: it explains the threat model, the file-encryption workflow, the session model, and the tech stack behind the tool. It is more than a generic blog index because the post describes a concrete desktop security system for local AI tools and includes implementation details and a repo link.
The crawl stops partway through the article, so visitors cannot see the full product scope, installation steps, screenshots, licensing details, or whether the project is actively maintained. The page also does not show a live demo or a concise feature list separate from the narrative.
Last evaluated 41 hours ago. Current rank #743. Down 2 spots in the rankings.
Open-source security scanner for AI agents, MCP servers, and agent skills. It auto-discovers installed agent components and checks them for prompt injection, tool poisoning, secrets, malware payloads, and related risks.
Self-hosted AI security testing platform for authorized pentesting and bug bounty workflows, with a local web UI, live agent telemetry, verified findings, and branded PDF reports.
GitHub Marketplace app from NeuraLegion that scans apps and APIs for vulnerabilities, proposes fixes, and validates remediations inside GitHub workflows.
Kernel-level read gate for AI coding agents that blocks protected file reads before bytes reach the agent, with Linux fanotify and macOS Endpoint Security support.
