#
prompt-injection
Here are 95 public repositories matching this topic...
Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.
python rust security cryptography typescript mcp delegation authorization capabilities access-control agents temporal ai-agents proof-of-possession a2a llm langchain prompt-injection langgraph agent-security
-
Updated
Oct 1, 2026 - Rust
Prompt injection scanner for AI coding tools (Claude Code / Codex / etc). Runs DeBERTa/Llama transformers via Candle or ONNX in Rust
-
Updated
Jul 28, 2026 - Rust
A trustless MCP server that replaces the generic shell tool with validated, sandboxed, purpose-built execution tools for AI coding agents.
rust cli security mcp sandbox developer-tools ai-agents prompt-injection model-context-protocol mcp-server claude-code coding-agent
-
Updated
Apr 13, 2026 - Rust
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth, passkeys, anti-bot reach, on-by-default prompt-injection defense, plus on-device multimodal ASR/OCR. A single Rust binary — not a browser.
markdown rust cli ocr mcp cookies anti-bot http3 asr ai-agents multimodal passkeys llm prompt-injection llm-tools llm-agents model-context-protocol claude-code url-to-markdown web-fetch
-
Updated
Sep 29, 2026 - Rust
Soup Wall: a local firewall for what an AI agent does - tool calls, tool results, MCP handshakes, subagents. Deterministic, shadow-first, no account, no network.
rust security mcp firewall appsec ai-agents prompt-injection llm-security agent-security claude-code
-
Updated
Sep 25, 2026 - Rust
Deterministic security analysis for agent skill files.
rust security mcp static-analysis sarif ai-agents supply-chain-security prompt-injection skill-files
-
Updated
Sep 24, 2026 - Rust
A zero-Python, production-grade LLM security layer written in Rust.
-
Updated
Sep 12, 2026 - Rust
Fleet AI Security Posture Management (AI-SPM): client agents on each developer machine score their AI coding agents' guard surfaces (Claude Code, Cursor, Codex, Gemini CLI — permissions, hooks, sandboxes, mcp.json) and ship hash-anchored events to a central server + your SIEM. Fleet-wide posture; measures, doesn't block. Rust.
rust security mcp cybersecurity cursor siem soc codex ai-security endpoint-security detection-engineering developer-security ai-agent prompt-injection gemini-cli claude-code mcp-security ai-coding-agent tool-poisoning ai-spm
-
Updated
Sep 24, 2026 - Rust
Pure-Rust prompt-injection detector with 1.5MB embedded MLP classifier. 98.40% accuracy, p50 14ms CPU inference, bindings for Python/JS/Go. Apache-2.0/MIT alternative to Rebuff (archived) and Lakera Guard.
nodejs rust golang machine-learning neural-network python-bindings ai-safety security-tools jailbreak-detection onnx ai-security guardrails embedded-ml prompt-injection llm-security llm-firewall prompt-guard prompt-injection-detection rebuff-alternative lakera-alternative
-
Updated
Aug 13, 2026 - Rust
The zero-trust framework for autonomous AI agents.
kubernetes rust devops ai kata sandbox self-hosted alignment ai-agents zero-trust gvisor cilium agent-framework kyverno prompt-injection agent-runtime agentic-security
-
Updated
Sep 22, 2026 - Rust
Transparent OpenAI-compatible security gateway for LLM agents — DLP, secret-leak, jailbreak & prompt-injection detection at the egress. Open-source core of AgentSentry, by Akav Labs.
-
Updated
Jul 30, 2026 - Rust
Codex 保安：OpenAI Codex 本机安全审计。实时发现高危命令、凭据访问、提示注入与投毒篡改；只读日志，不代理、不装证书。
windows security mcp openai codex ai-agents tauri ai-security guardrails local-first openai-codex prompt-injection llm-security codex-cli
-
Updated
Sep 30, 2026 - Rust
Local coding-agent control plane — MCP action governance + LLM-path protection + cost control. One Rust binary, no SaaS.
rust caching privacy ai proxy mcp openai developer-tools cursor claude ai-tools llm prompt-injection anthropic ollama context-window coding-agents agent-security
-
Updated
Sep 28, 2026 - Rust
Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI — blocks dangerous commands, detects prompt injection, and prevents PII leakage before it happens.
open-source cursor commnad prompt-injection gemini-cli claude-code runtime-security-guardrails kiteguard-cli
-
Updated
Apr 3, 2026 - Rust
Argorix Lang is a compiled language for secure, verifiable AI-agent communication.
bytecode compiler virtual-machine rust-lang secure-communication ai-safety ai-agents prompt-injection ai-agents-framework deterministic-systems agentic-ai agent-security
-
Updated
Sep 28, 2026 - Rust
A standalone agent harness in Rust: a provider-agnostic loop, MCP tools, a path jail and prompt-injection interlock, sandboxed shell, scheduled triggers, and an eval rig that grades the trace.
rust cli mcp tui claude agent-framework ai-agent llm prompt-injection anthropic llm-agent llm-evaluation agentic-ai model-context-protocol
-
Updated
Oct 1, 2026 - Rust
Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.
shell rust cli security ai proxy devtools command-line-tool ai-safety ai-agents guardrails secrets-detection rust-cli terminal-proxy llm prompt-injection llm-security agentic-ai claude-code secret-redaction
-
Updated
Sep 7, 2026 - Rust
Lightweight, local-first security testing command-line tool (CLI) built in Rust that scans LLM wrappers, RAG databases, and autonomous AI agents for OWASP Top 10 vulnerabilities
-
Updated
Sep 9, 2026 - Rust
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
react rust typescript mcp cybersecurity claude zero-trust security-research tauri ai-security prompt-injection llm-security model-context-protocol
-
Updated
Sep 25, 2026 - Rust
Add this topic to your repo
To associate your repository with the prompt-injection topic, visit your repo's landing page and select "manage topics."