Skip to content
View themayursinha's full-sized avatar
🤖
🤖
13 followers · 2 following

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Pull Sharkx2

Organizations

@intellisentry

Block or report themayursinha

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
themayursinha/README.md

Mayur Sinha

> Staff Security engineer building deterministic control planes for AI agents.
> Currently: platform & product security · detection engineering · incident response.
> Building: deterministic enforcement at the tool boundary, not inside the prompt.
> Writing: https://themayursinha.com
> Prompts guide. Specs enforce. Boundaries decide.

Pinned Loading

  1. mcp-visor mcp-visor Public

    Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.

    Go 5

  2. adversarial-ml-lab adversarial-ml-lab Public

    Interactive demonstrations of adversarial ML attacks & defenses. Prompt injection, context tampering, inference evasion

    Python

  3. mcp-llm-security-evaluator mcp-llm-security-evaluator Public

    Security focused tooling for testing how an LLM behaves when it is exposed to sensitive text, repository content, and MCP-style tool access. The project can run local smoke tests with a determinist…

    Python

  4. awesome-agentic-ai-security awesome-agentic-ai-security Public

    Curated tools, papers, and resources for securing agentic AI — runtimes, tool boundaries, MCP, and policy enforcement.

    1

  5. security-assessments-scripts security-assessments-scripts Public

    This is a collection of various python scripts to get through security assessments.

    Python

  6. vuln-research-harness vuln-research-harness Public

    Deterministic campaign harness for authorized AI-assisted vulnerability research

    Go