{"data":{"slug":"tencent-ai-infra-guard","name":"AI-Infra-Guard","tagline":"A full-stack AI Red Teaming platform securing AI ecosystems","github_url":"https://github.com/Tencent/AI-Infra-Guard","owner":"Tencent","repo":"AI-Infra-Guard","owner_avatar_url":"https://avatars.githubusercontent.com/u/18461506?v=4","primary_language":"Python","stars":4316,"forks":419,"topics":["agent","agent-security","ai-infra","ai-red-teaming","ai-security","llm","llm-evaluation","llm-jailbreak","llm-security","mcp-scan","openclaw-security","prompt-injection","prompt-security","scanner","security","security-tools","skill-scanner","skills-security","vulnerability"],"archived":false,"github_pushed_at":"2026-07-28T10:33:46+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/tencent-ai-infra-guard","markdown_url":"https://www.graphcanon.com/tools/tencent-ai-infra-guard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tencent-ai-infra-guard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tencent-ai-infra-guard","description":"A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.","homepage_url":"https://tencent.github.io/AI-Infra-Guard/","license":"Apache-2.0","open_issues":13,"watchers":37,"ai_summary":"Tencent/AI-Infra-Guard is a comprehensive security solution for AI ecosystems providing tools for agent scanning, skill assessment, and LLM jailbreak evaluation to ensure the integrity and safety of AI infrastructures.","readme_excerpt":"### 🐳 Deploy A.I.G with Docker\n\n| Docker | RAM | Disk Space |\n|:-------|:----|:----------|\n| 20.10 or higher | 4GB+ | 10GB+ |\n\n```bash\n\n---\n\n# This method pulls pre-built images from Docker Hub for a faster start\ngit clone https://github.com/Tencent/AI-Infra-Guard.git\ncd AI-Infra-Guard\n\n---\n\n# For Docker Compose V2+, replace 'docker-compose' with 'docker compose'\ndocker-compose -f docker-compose.images.yml up -d\n```\n\nOnce the service is running, you can access the A.I.G web interface at:\n`http://localhost:8088`\n<br>\n\n#### Use from OpenClaw\n\nYou can also call A.I.G directly from OpenClaw chat via the `aig-scanner` skill.\n\n```bash\nclawhub install aig-scanner\n```\n\nThen configure `AIG_BASE_URL` to point to your running A.I.G service.\n\nFor more details, see the [`aig-scanner` README](./skills/aig-scanner/README.md).\n\n<details>\n<summary><strong>More installation options</strong></summary>\n\n---\n\n### Other Installation Methods\n\n**Method 2: One-Click Install Script （Recommended）**\n```bash\n\n---\n\n# This method will automatically install Docker and launch A.I.G with one command\ncurl https://raw.githubusercontent.com/Tencent/AI-Infra-Guard/refs/heads/main/docker.sh | bash\n```\n\n**Method 3: Build and run from source**\n```bash\ngit clone https://github.com/Tencent/AI-Infra-Guard.git\ncd AI-Infra-Guard\n\n---\n\n# This method builds a Docker image from local source code and starts the service\n\n---\n\n# (For Docker Compose V2+, replace 'docker-compose' with 'docker compose')\ndocker-compose up -d\n```\n\nNote: The AI-Infra-Guard project is positioned as an AI red teaming platform for internal use by enterprises or individuals. It currently lacks an authentication mechanism and should not be deployed on public networks.\n\nFor more information, see: [https://tencent.github.io/AI-Infra-Guard/?menu=getting-started](https://tencent.github.io/AI-Infra-Guard/?menu=getting-started)\n\n</details>\n\n---\n\n### ⚡ Install aig-skill-scan with a Single Command\n\nAgent Skill security audit tool, easily integrated into enterprise CI/CD pipelines. Vulnerability classification aligns with [SkillTrustBench](https://matrix.tencent.com/skilltrustbench/) T01–T09 taxonomy. [Learn more →](https://github.com/Tencent/AI-Infra-Guard/tree/main/skill-scan)\n\n```bash\npip install aig-skill-scan\n\n---\n\n### AI Infrastructure Vulnerability Scan\n\n**What to enter as the target URL / IP?**\n\nThe target is the **network address of a running AI service** you want to scan - not a GitHub URL or source code path. A.I.G connects to the live service and fingerprints it for known CVE vulnerabilities.\n\n| Scenario | Example target |\n|:---------|:--------------|\n| A locally running vLLM instance | `http://127.0.0.1:8000` |\n| An Ollama server on your LAN | `http://192.168.1.100:11434` |\n| A ComfyUI instance exposed internally | `http://10.0.0.5:8188` |\n| Multiple hosts (one per line) | `192.168.1.0/24` (CIDR), `10.0.0.1-10.0.0.20` (range) |\n\n**Step-by-step: Scan a local vLLM instance**\n\n1. Start vLLM normally (e.g. `python -m vllm.entrypoints.api_server --model meta-llama/...`)\n2. In the A.I.G web UI, click **\"AI基础设施安全扫描 / AI Infra Scan\"**\n3. Enter `http://127.0.0.1:8000` (or the IP/port where vLLM is listening)\n4. Click **Start Scan** - A.I.G will fingerprint the service and match it against 1900+ known CVEs\n5. View the report: component version, matched vulnerabilities, severity, and remediation links\n\n> 💡 **Tip**: To scan the *nightly* build of vLLM specifically, just run that nightly build and point A.I.G at its address. The scanner detects the version automatically.\n\n---\n\n## ⚖️ License & Attribution\n\nThis project is open-sourced under the **Apache License 2.0**. We warmly welcome and encourage community contributions, integrations, and derivative works, subject to the following attribution requirements:\n\n1. **Retain notices**: You must retain the `LICENSE` and `NOTICE` files from the original project in any distribution.\n2. **Product attribution**: If you integrate AI-Infra-Guard's core code, components, or","github_created_at":"2024-12-25T06:39:30+00:00","created_at":"2026-07-11T11:59:15.96671+00:00","updated_at":"2026-07-28T12:00:28.23067+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agent-security","name":"agent-security"},{"slug":"ai-red-teaming","name":"ai-red-teaming"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"security-tools","name":"security-tools"},{"slug":"skills-security","name":"skills-security"}],"trust":{"provenance":{"is_fork":false,"github_id":908108028,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-28T12:00:27.268Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":9,"days_since_push":0,"last_release_at":"2026-07-27T07:21:58Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:59:17.174Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-28T12:00:27.711Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-28T12:00:27.711Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-28T12:00:27.711Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-28T12:00:27.711Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-28T12:00:27.711Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If you need advanced LLM jailbreak evaluation capabilities specific to the vulnerabilities identified by Tencent's research, consider using AI-Infra-Guard.","Suitable when your organization requires security assessments that go beyond just code but also cover skill assessments for AI-driven tasks or environments."],"when_not_to_use":["Avoid if you are looking exclusively for a tool that focuses solely on the runtime behavior of LLMs without broader infrastructural scanning capabilities.","Not recommended when your primary focus is on network-level security rather than comprehensive AI infrastructure security assessments and evaluations."],"source":"enrich:decision_facts","observed_at":"2026-07-17T13:09:32.237Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"AI-Infra-Guard is designed for organizations looking to secure their AI infrastructures comprehensively through various scanning and evaluation tools."}]}}