llm-security — independent software & tools

17 independent llm-security listings the big search engines bury.

• huqan

  github · Free · by ali-ulu

  Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.

• attestral

  github · Free · by attestral-labs

  Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency, and models the cloud your agents can reach. pip install attestral.

• AI-Security-Platform

  github · Free · by Bobcatsfan33

  Control plane for enterprise AI security: inline runtime guardrails, automated red teaming with auto-remediation, AI asset posture (AI-SPM), and compliance governance. Python control plane + Go inline agent.

• conarium

  github · Free · by dogrucanemek-alt

  Conarium AI — self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, an Ed25519-signed receipt per access verifiable offline, coverage reconciliation against the DB's own query counters to surface gateway bypasses, and conformance vectors. MCP-native. MIT.

• clawseccheck

  github · Free · by gl0di

  🦞 Free, local, read-only security self-audit for your own OpenClaw AI-agent setup. Scores it A–F, surfaces the urgent holes, emits copy-paste fixes. Zero deps, no network, no API key — your data never leaves your machine.

• ai-privacy-gateway

  github · Free · by gunxueqiu6

  你的 AI 数据正在裸奔，30 秒装上防火墙。开源的 AI API 隐私隔离网关。

• crewscore

  github · Free · by shmindmaster

  Find the safety rules your AI agent prompt forgot. Checks 23 published controls — injection defense, human approval, cost limits, stop conditions. Offline CLI + GitHub Action + in-browser checker. No API key, no LLM.

• mcp-safeguard

  github · Free · by SyedAnas01

  🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 52 rules for prompt injection, credential exposure, SSRF & tool poisoning. pip install mcp-safeguard

• pentest-mcp-server

  github · Free · by wallieinformal201

  Integrate penetration testing tools and payloads into your workflow through the Model Context Protocol using STDIO or HTTP.

• tool-gates

  github · Free · by camjac251

  Intelligent tool permission gate & security hooks for AI assistants (Claude Code, Codex, Antigravity; Gemini deprecated). Features AST shell gating, file guards, and safety scanners.

• MCPScan

  github · Free · by harikrishn4101

  Scan and identify security issues in MCP servers to help strengthen defenses against potential attacks on AI agent connections.

• agent-bom

  github · Free · by msaad00

  AI supply-chain & cloud security scanner and self-hosted control plane — agents, MCP, packages, cloud estate, non-human identities, and LLM cost. SBOM/SARIF, graph attack-paths, runtime enforcement, and compliance evidence.

• agent-bom

  github · Free · by msaad00

  Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings, govern in your VPC.

• nuguard

  github · Free · by NuGuardAI

  AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

• hackmyagent

  github · Free · by opena2a-org

  Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.

• synentra

  github · Free · by synentra

  Intent‑aware governance gateway for autonomous AI agents that interact with enterprise APIs.

• ZugaShield

  github · Free · by Zuga-Technologies

  7-layer AI agent security system — stop prompt injection, data exfiltration, and AI-specific attacks in under 15ms. Zero dependencies.