{
 "schema_version": 1,
 "generated": "2026-10-29",
 "url": "https://dedupedai.com/best-ai-repos-for/securing-ai-coding-agents/",
 "task": "securing AI coding agents",
 "question": "What are the best open-source tools to secure AI coding agents and the skills they install?",
 "answer": "The best open-source AI repos for securing AI coding agents right now are SkillSpector, SolonGate Agent Security and jev-guard. Scan third-party skills and MCP servers with SkillSpector before you install them, then gate the agent's tool calls: SolonGate Agent Security checks calls against policy and catches secrets, jev-guard returns deny, ask or allow for each call, and Tracekit signs every call and decision into a tamper-evident log you can verify offline.",
 "md": "https://dedupedai.com/best-ai-repos-for/securing-ai-coding-agents/index.md",
 "repos": [
  {
   "repo": "NVIDIA/SkillSpector",
   "title": "SkillSpector",
   "url": "https://dedupedai.com/use-cases/nvidia-skillspector/",
   "github": "https://github.com/NVIDIA/SkillSpector",
   "what": "SkillSpector is NVIDIA's security scanner for AI agent skills used by Claude Code, Codex CLI, Gemini CLI and others. It scans Git repos, URLs, zips, directories or single files for 71 vulnerability patterns in 17 categories, including prompt injection, data exfiltration and MCP tool poisoning, with fast static analysis plus optional LLM evaluation, live OSV.dev CVE lookups, a 0 to 100 risk score and Terminal, JSON, Markdown or SARIF reports.",
   "who": "Developers and security teams who install third-party agent skills or MCP servers and want to know whether they are safe first.",
   "stars": 22109,
   "language": "Python",
   "requirements": [
    "Python with uv or pip, or Docker (no Python required)",
    "Optional: an LLM API key in .env for semantic analysis (default config targets DeepSeek)",
    "Optional MCP extra for skillspector mcp"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Scan an agent skill for prompt injection and exfiltration before installing",
     "url": "https://dedupedai.com/use-cases/nvidia-skillspector/scan-an-agent-skill-before-installing/"
    },
    {
     "title": "Gate skill updates in CI so only new findings fail",
     "url": "https://dedupedai.com/use-cases/nvidia-skillspector/gate-skill-changes-with-a-baseline/"
    },
    {
     "title": "Spot new or changed MCP servers between registry snapshots",
     "url": "https://dedupedai.com/use-cases/nvidia-skillspector/compare-mcp-registry-snapshots/"
    }
   ],
   "best": {
    "title": "Scan an agent skill for prompt injection and exfiltration before installing",
    "url": "https://dedupedai.com/use-cases/nvidia-skillspector/scan-an-agent-skill-before-installing/",
    "difficulty": "Beginner",
    "time": "10 minutes",
    "agents": [
     "claude-code",
     "codex",
     "gemini-cli"
    ],
    "steps": [
     "Install with uv tool install git+https://github.com/NVIDIA/skillspector.git",
     "Download or clone the skill you want to check",
     "Scan it without LLM costs using Docker: docker run --rm -v \"$PWD:/scan\" skillspector scan ./my-skill/ --no-llm",
     "Read the risk score, severity labels and recommendations",
     "Install the skill only if the findings are acceptable"
    ],
    "md": "https://dedupedai.com/use-cases/nvidia-skillspector/scan-an-agent-skill-before-installing/index.md"
   }
  },
  {
   "repo": "solongate/agent-security",
   "title": "SolonGate Agent Security",
   "url": "https://dedupedai.com/use-cases/solongate-agent-security/",
   "github": "https://github.com/solongate/agent-security",
   "what": "SolonGate Agent Security is a local, open-source Go gateway that checks AI coding agent tool calls against policy, detects secrets, and writes an on-device audit trail.",
   "who": "Developers and security-minded engineers who run AI coding agents on their own machines and want to control what those agents can read, write, and send.",
   "stars": 156,
   "language": "Go",
   "requirements": [
    "A machine where you can run a shell and git (the README installs with git clone and ./scripts/shell/install.sh)",
    "Claude Code or Codex installed as the agent you want to guard",
    "A new terminal after install, since hooks load only when a session starts",
    "For the sandbox use case: Linux with bubblewrap (bwrap) installed, since the README says it is required and macOS and Windows refuse"
   ],
   "uc_count": 4,
   "use_cases": [
    {
     "title": "Stop an AI coding agent from reading your .env secrets",
     "url": "https://dedupedai.com/use-cases/solongate-agent-security/block-agent-access-to-env-secrets/"
    },
    {
     "title": "Lock files so a coding agent cannot delete or edit them",
     "url": "https://dedupedai.com/use-cases/solongate-agent-security/lock-files-against-agent-edits/"
    },
    {
     "title": "Confine a coding agent to one project folder on Linux",
     "url": "https://dedupedai.com/use-cases/solongate-agent-security/confine-agent-to-one-project-on-linux/"
    }
   ],
   "best": {
    "title": "Stop an AI coding agent from reading your .env secrets",
    "url": "https://dedupedai.com/use-cases/solongate-agent-security/block-agent-access-to-env-secrets/",
    "difficulty": "Intermediate",
    "time": "30 minutes",
    "agents": [
     "claude-code",
     "codex"
    ],
    "steps": [
     "git clone https://github.com/solongate/agent-security.git",
     "cd agent-security",
     "./scripts/shell/install.sh",
     "Open a new terminal, then start Claude Code or Codex in your project.",
     "Ask the agent to read the .env file, then run solongate audit to confirm the refusal was logged."
    ],
    "md": "https://dedupedai.com/use-cases/solongate-agent-security/block-agent-access-to-env-secrets/index.md"
   }
  },
  {
   "repo": "leepokai/jev-guard",
   "title": "jev-guard",
   "url": "https://dedupedai.com/use-cases/leepokai-jev-guard/",
   "github": "https://github.com/leepokai/jev-guard",
   "what": "jev-guard is a security hook for coding agents that scores each tool call with session context and returns deny, ask, or allow, flags prompt injection in tool results, and checks skills and plugins, powered by Jev.",
   "who": "Developers who run coding agents such as Claude Code, Codex, Cursor or Gemini CLI on real repositories and want an extra approval layer before risky commands run.",
   "stars": 127,
   "language": "JavaScript",
   "requirements": [
    "Node.js and npm, to install the jev-guard package or run the install commands",
    "One provider key: a TypeSafe key from console.typesafe.ai, a vck_ Vercel AI Gateway key, or an sk-or- OpenRouter key",
    "The coding agent you want to guard, installed on the same machine"
   ],
   "uc_count": 5,
   "use_cases": [
    {
     "title": "Guard Claude Code tool calls with deny and ask decisions",
     "url": "https://dedupedai.com/use-cases/leepokai-jev-guard/guard-claude-code-tool-calls/"
    },
    {
     "title": "Scan agent skills and plugins for unexpected behavior",
     "url": "https://dedupedai.com/use-cases/leepokai-jev-guard/scan-skills-and-plugins-before-install/"
    },
    {
     "title": "Add a guard layer to Codex through its plugin browser",
     "url": "https://dedupedai.com/use-cases/leepokai-jev-guard/guard-codex-with-hook-trust/"
    }
   ],
   "best": {
    "title": "Guard Claude Code tool calls with deny and ask decisions",
    "url": "https://dedupedai.com/use-cases/leepokai-jev-guard/guard-claude-code-tool-calls/",
    "difficulty": "Intermediate",
    "time": "15 minutes",
    "agents": [
     "claude-code"
    ],
    "steps": [
     "Run npm i -g jev-guard",
     "Run jev-guard key \"…\" with your TypeSafe, Vercel AI Gateway or OpenRouter key",
     "Run jev-guard install claude",
     "Start Claude Code and run a harmless command, then run jev-guard check Bash '{\"command\":\"rm -rf ~/\"}' to confirm the deny output"
    ],
    "md": "https://dedupedai.com/use-cases/leepokai-jev-guard/guard-claude-code-tool-calls/index.md"
   }
  },
  {
   "repo": "Cygnux-Labs/Tracekit",
   "title": "Tracekit",
   "url": "https://dedupedai.com/use-cases/cygnux-labs-tracekit/",
   "github": "https://github.com/Cygnux-Labs/Tracekit",
   "what": "Tracekit is a Python tool that gates each AI agent tool call before it runs, signs every call and decision into a tamper-evident hash chain, and lets anyone verify each run offline.",
   "who": "Developers and security or audit reviewers who need to see what an AI agent did, whether it was allowed, and whether the record can be trusted.",
   "stars": 244,
   "language": "Python",
   "requirements": [
    "Python 3.9 to 3.13 (framework integrations need 3.10 or newer), or uv for the one-line demo",
    "A terminal on your own machine; runs on your own machines per the README",
    "Dev mode runs as your user, so it protects nothing against an agent running as you"
   ],
   "uc_count": 4,
   "use_cases": [
    {
     "title": "See a denied command and a tamper check in 5 seconds",
     "url": "https://dedupedai.com/use-cases/cygnux-labs-tracekit/see-denied-call-and-tamper-check/"
    },
    {
     "title": "Record every tool call of a Python agent run",
     "url": "https://dedupedai.com/use-cases/cygnux-labs-tracekit/record-python-agent-run/"
    },
    {
     "title": "Check a run file offline against a key you pinned",
     "url": "https://dedupedai.com/use-cases/cygnux-labs-tracekit/verify-run-file-offline/"
    }
   ],
   "best": {
    "title": "See a denied command and a tamper check in 5 seconds",
    "url": "https://dedupedai.com/use-cases/cygnux-labs-tracekit/see-denied-call-and-tamper-check/",
    "difficulty": "Beginner",
    "time": "15 minutes",
    "agents": [],
    "steps": [
     "Install uv from https://docs.astral.sh/uv/ if you do not have it.",
     "Run uvx --from tracekit-ai tracekit demo --server.",
     "Read the agent run lines: Bash 'sudo rm -rf /' shows deny, and the first Integrity line says VERIFIED.",
     "Read the tamper test: the rewritten copy shows [FAIL] signatures and Integrity: FAILED at the changed record."
    ],
    "md": "https://dedupedai.com/use-cases/cygnux-labs-tracekit/see-denied-call-and-tamper-check/index.md"
   }
  },
  {
   "repo": "Mah3Sec/ForgeGuardian",
   "title": "ForgeGuardian",
   "url": "https://dedupedai.com/use-cases/mah3sec-forgeguardian/",
   "github": "https://github.com/Mah3Sec/ForgeGuardian",
   "what": "ForgeGuardian is a local-first, Go-based software supply chain security scanner that checks project dependencies across 9 ecosystems with 8 scan engines.",
   "who": "Developers and security engineers who need to check a project's dependencies for known CVEs and malicious packages before shipping.",
   "stars": null,
   "language": "Go",
   "requirements": [
    "A terminal (bash on Linux or macOS, or PowerShell on Windows), or Docker",
    "A project directory with dependencies to scan",
    "Git and make only if building from source"
   ],
   "uc_count": 4,
   "use_cases": [
    {
     "title": "Scan project dependencies for risks before release",
     "url": "https://dedupedai.com/use-cases/mah3sec-forgeguardian/scan-project-dependencies-locally/"
    },
    {
     "title": "Fail CI builds on high-severity dependency findings",
     "url": "https://dedupedai.com/use-cases/mah3sec-forgeguardian/gate-ci-builds-on-high-severity-findings/"
    },
    {
     "title": "Generate an SBOM for a project in the dashboard",
     "url": "https://dedupedai.com/use-cases/mah3sec-forgeguardian/build-sbom-for-a-workspace/"
    }
   ],
   "best": {
    "title": "Scan project dependencies for risks before release",
    "url": "https://dedupedai.com/use-cases/mah3sec-forgeguardian/scan-project-dependencies-locally/",
    "difficulty": "Beginner",
    "time": "15 minutes",
    "agents": [],
    "steps": [
     "Install Forge Guardian with curl -sSfL https://raw.githubusercontent.com/Mah3Sec/ForgeGuardian/main/install.sh | bash",
     "Run fgctl update to refresh the community signatures",
     "Change into your project folder and run fgctl scan .",
     "Read the findings, noting severity and the fix version listed for each",
     "If an optional engine such as Grype, Trivy, or Semgrep is missing, run fgctl doctor --fix, then scan again"
    ],
    "md": "https://dedupedai.com/use-cases/mah3sec-forgeguardian/scan-project-dependencies-locally/index.md"
   }
  }
 ]
}