AI-Surface
Find and govern AI attack surfaces in application code at PR time. Free, OSS, runs offline.
File Explorer
Download Latest Version (.zip)- entry.py
- bug.yml
- config.yml
- false-negative.yml
- false-positive.yml
- feature-request.yml
- example-pr-check.yml
- publish.yml
- security-scan.yml
- self-test.yml
- dependabot.yml
- pull_request_template.md
- overview-governance.png
- state-of-ai-surface.png
- surface-map.png
- ARCHITECTURE.md
- CI_INTEGRATION.md
- COMPLIANCE.md
- DETECTORS.md
- LANGUAGE_SUPPORT.md
- PRIVACY.md
- SCHEMA_v1.md
- STATE_OF_AI_SURFACE.md
- bedrock.tf
- vllm-embeddings.yaml
- api.py
- chat_agent.py
- knowledge_base.py
- llm_service.py
- orders_mcp_server.py
- support_workflow.py
- .env.example
- .mcp.json
- litellm.config.yaml
- README.md
- circleci.yml
- gitlab-ci.yml
- pre-commit-hook.sh
- pr-comment.md
- report.json
- report.md
- terminal.txt
- basic.yml
- custom-risk-threshold.yml
- fail-on-risk.yml
- scan-on-main.yml
- README.md
- demo_report.json
- generate_demo.py
- generate_sample.py
- sample_report.json
- __init__.py
- api_patterns.py
- known_mcps.json
- model_patterns.py
- owasp_llm.py
- registry.py
- risk_definitions.py
- secret_patterns.py
- __init__.py
- __init__.py
- agent_frameworks.py
- ai_infra.py
- api_endpoints.py
- env_keys.py
- llm_sdks.py
- mcp_audit.py
- mcp_servers.py
- model_gateways.py
- vector_rag.py
- __init__.py
- cyclonedx_reporter.py
- json_reporter.py
- markdown_reporter.py
- sarif_reporter.py
- terminal_reporter.py
- ai-bom.json
- app.js
- index.html
- README.md
- report.json
- styles.css
- __init__.py
- markdown_safety.py
- specs.py
- walk.py
- __init__.py
- audits.py
- cli.py
- cross_promo.py
- diff.py
- dispositions.py
- frameworks.py
- observability.py
- orchestrator.py
- oversight.py
- pii.py
- repo.py
- types.py
- ui_server.py
- verdicts.py
- anthropic_tools.py
- claude_agent_sdk_app.py
- claude_agent_sdk_app.ts
- clean.py
- crewai_research.py
- langchain_refund.py
- openai_agents_refund.py
- strands_param_hydration.py
- foo.py
- docker-compose.yml
- Dockerfile
- Dockerfile
- values.yaml
- deployment.yaml
- deployment.yaml
- main.tf
- routes.js
- main.py
- openapi.yaml
- main.py
- .mcp.json
- openapi.yaml
- .env
- .envrc
- .env
- .env.production
- foo.py
- config.yaml
- app.py
- .env
- .mcp.json
- api.py
- assistant.ts
- knowledge.py
- prompts.py
- support_agent.py
- agent.py
- client.ts
- utils.py
- summarize.py
- README.txt
- regular_app.py
- mcp.json
- mcp_orders_server.py
- __init__.py
- test_agent_frameworks.py
- test_ai_infra.py
- test_api_endpoints.py
- test_audits.py
- test_cli.py
- test_cross_promo.py
- test_cross_promo_bridges.py
- test_cyclonedx.py
- test_diff.py
- test_dispositions.py
- test_e2e.py
- test_edge_cases.py
- test_env_keys.py
- test_frameworks.py
- test_gate.py
- test_golden_app.py
- test_governance_flag.py
- test_init_command.py
- test_llm_sdks.py
- test_markdown_safety.py
- test_mcp_audit.py
- test_mcp_reach.py
- test_mcp_servers.py
- test_model_gateways.py
- test_observability.py
- test_orchestrator.py
- test_oversight.py
- test_pii.py
- test_redos.py
- test_repo_scan.py
- test_reporters.py
- test_sarif.py
- test_ui_server.py
- test_vector_rag.py
- test_verdicts.py
- test_walk.py
- .gitignore
- .pre-commit-hooks.yaml
- action.yml
- CHANGELOG.md
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- Dockerfile
- LICENSE
- pyproject.toml
- README.md
- SECURITY.md
# Installation Guide
1. Get the code
git clone https://github.com/apisec-inc/AI-Surface
Downloads the entire project code from GitHub to your computer.
cd AI-Surface
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
pipx install apisec-ai-surface
Installs the CLI tool into an isolated environment via pipx.
pip install apisec-ai-surface && ai-surface scan .
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Docker
EasyPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -t ai-surface .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 ai-surface
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
4. Python
EasyPrerequisites
pip install apisec-ai-surface && ai-surface scan .
Installs the package published on PyPI directly β no need to clone the source.
python -m venv .venv
Runs the Python script (or module).
pip install -e ".[dev]"
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)