indirect-prompt-injection repositories

Trending repositories tagged indirect-prompt-injection, ranked by trending score. Updated daily.

  1. 1
    Agentic-AI-Risk-Mitigation/Janus

    System-level security for LLM agents: fine-grained policy enforcement on tool calls to defend against indirect prompt injection

    GitHub · Python · 22 stars · 2 forks · +4 stars in 24 hours · Trending score 1.06

  2. 2
    StackOneHQ/defender

    Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.

    GitHub · TypeScript · 137 stars · 14 forks · 0 stars in 24 hours · Trending score 0.82

  3. 3
    shoebpate1/ai-agent-hacking-writeups

    A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

    GitHub · 52 stars · 3 forks · 0 stars in 24 hours · Trending score 0.53

  4. 4
    ilyautov/cordon

    A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Gemini CLI, MCP hosts and LangChain. | Файрвол от промпт-инъекций для ИИ-агентов без ИИ внутри: агент читает что угодно и слушается только вас.

    GitHub · TypeScript · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00