Skip to content
New

DeepSeek V4.1 Flash free for 7 days: 10M tokens a day after a top-up of $10 or more. Until Nov 30.

How it works

AI, agents and MCP

Prompt injection, RAG poisoning, MCP servers, agent permissions and model supply chain.

Assessing LLM apps and agents: tool output trust, MCP server code audits, sandbox and secret exposure, model artifacts, vector database security and AI red team test plans.

Results

  1. testing-prompt-injection-in-rag-pipelines

    High
    mukul975/testing-prompt-injection-in-rag-pipelines
    4 installs, 4 installs in the last 7 days, 36,301 stars on GitHub
  2. implementing-llm-guardrails-for-security

    High
    mukul975/implementing-llm-guardrails-for-security
    4 installs, 4 installs in the last 7 days, 36,301 stars on GitHub
  3. defending-llms-with-guardrails

    High
    mukul975/defending-llms-with-guardrails
    4 installs, 4 installs in the last 7 days, 36,301 stars on GitHub
  4. testing-for-system-prompt-leakage

    High
    mukul975/testing-for-system-prompt-leakage
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  5. detecting-indirect-prompt-injection

    High
    mukul975/detecting-indirect-prompt-injection
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  6. detecting-ai-model-prompt-injection-attacks

    High
    mukul975/detecting-ai-model-prompt-injection-attacks
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  7. auditing-mcp-servers-for-tool-poisoning

    High
    mukul975/auditing-mcp-servers-for-tool-poisoning
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  8. assessing-vector-and-embedding-weaknesses

    High
    mukul975/assessing-vector-and-embedding-weaknesses
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  9. securing-agentic-ai-tool-invocation

    Medium
    mukul975/securing-agentic-ai-tool-invocation
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  10. red-teaming-llms-with-garak

    Medium
    mukul975/red-teaming-llms-with-garak
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  11. performing-ai-driven-osint-correlation

    Medium
    mukul975/performing-ai-driven-osint-correlation
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  12. orchestrating-llm-attacks-with-pyrit

    Medium
    mukul975/orchestrating-llm-attacks-with-pyrit
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  13. detecting-model-extraction-attacks

    Medium
    mukul975/detecting-model-extraction-attacks
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  14. detecting-business-email-compromise-with-ai

    Medium
    mukul975/detecting-business-email-compromise-with-ai
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
  15. continuous-llm-red-teaming-with-promptfoo

    Medium
    mukul975/continuous-llm-red-teaming-with-promptfoo
    3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub

Ask anything your scope allows.

Create an account, add credits and ask the first question in the chat or the terminal.

  1. 1/3

    Create the account

    Individual or company. You can switch to a company later without losing balance or keys.

    IndividualCompany
  2. 2/3

    Add credits

    By card. Pay per token, no subscription.

    $5.00minimum deposit
  3. 3/3

    Ask

    In the chat, or install the CLI and run notholy login in your terminal.

    $ notholy login