Skip to content
View asii-mov's full-sized avatar
😄
¯\_(ツ)_/¯
😄
¯\_(ツ)_/¯
3 followers · 1 following

Achievements

Achievement: Pull SharkAchievement: Pair Extraordinaire

Achievements

Achievement: Pull SharkAchievement: Pair Extraordinaire

Block or report asii-mov

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
asii-mov/README.md

asiimov

  • Working on: AppSec tooling for AI.
  • Learning: Machine Learning, Evals, and AI safety.
  • Contact Me

Projects:

  • Llama Guard Learning Loop - Still in progress, I am attempting to teach a safeguard to learn from blocked outputs by using its input prompt to stop attacks earlier
  • CodeSucks AI - SAST that leverages SemGrep and TruffleHog to find security issues with automated code patching using Anthropic's Claude & Claude Code
  • No Keys - Stop sending API keys to model providers by leveraging Python middleware

Pinned Loading

  1. Llama-Guard-Output-Feedback Llama-Guard-Output-Feedback Public

    A project to improve LLM safeguards by enhancing Meta's Llama Guard. It uses a learning mechanism to train the model on prompts that previously led to blocked outputs.

    Python 3

  2. codesucks-ai codesucks-ai Public

    SAST/AST Tool that leverages Semgrep MCP and Claude Code to conduct vulnerability scans and patches on GitHub

    Go 2

  3. mcproxy mcproxy Public

    Security-focused proxy server for the Model Context Protocol (MCP) protecting against injection attacks and security vulnerabilities

    TypeScript

  4. no-keys no-keys Public

    Stop sending API keys to model providers

    Python