Is my source code sent to ShipSafe servers?

Never. ShipSafe runs entirely on your machine. Scans, analysis, and auto-fixes all happen locally. Your source code never leaves your computer. No account required. Works offline.

How do I install ShipSafe?

Run: npm install -g @shipsafe/cli. Then run 'shipsafe scan' in any project directory. That's it — zero configuration required.

What does ShipSafe detect?

ShipSafe has 1,200+ detection rules covering SQL injection (127 rules), XSS (143 rules), prompt injection (7 rules), command injection (89 rules), SSRF (67 rules), hardcoded secrets (174 patterns), insecure authentication (98 rules), malicious MCP servers (30 patterns), path traversal, insecure deserialization, and more.

How is ShipSafe different from Snyk or SonarQube?

ShipSafe runs entirely locally (Snyk requires cloud), has AI-specific security rules like prompt injection and malicious MCP server detection (unique to ShipSafe), strips image metadata, and includes an MCP server for AI coding assistants. It's built for solo developers and small teams who use AI coding assistants.

Can I use ShipSafe with Claude, Cursor, or other AI tools?

Yes. ShipSafe includes an MCP server with 8 tools that plug directly into Claude, Cursor, Windsurf, and any other MCP-compatible assistant. Your AI can check security while it writes code.

What is prompt injection and does ShipSafe detect it?

Prompt injection is when untrusted user input is passed directly into LLM prompts, allowing attackers to manipulate AI behavior. ShipSafe has 7 dedicated rules that detect unsanitized user input in LLM prompts, system prompt leakage, indirect prompt injection via retrieved content, and prompt template manipulation.

What are malicious MCP servers and how does ShipSafe detect them?

Malicious MCP servers are rogue AI tool servers that can steal credentials, exfiltrate code, or inject malicious prompts. ShipSafe's scan-environment command checks your MCP configurations, CLAUDE.md files, git hooks, and npm scripts for 30 threat patterns including credential theft, data exfiltration, and prompt injection.

Yes. The free tier includes full security scanning with 1,200+ rules, git pre-commit hooks, baseline/delta mode, and support for 1 project. Pro ($19/mo) adds knowledge graph analysis, auto-fix, monitoring, and MCP server. Team ($49/mo) adds GitHub App integration and source maps.

How does ShipSafe reduce false positives?

ShipSafe uses Tree-sitter AST analysis to understand code context — it knows whether a variable comes from user input and whether it's been sanitized before reaching a dangerous sink. This context-aware detection dramatically reduces false positives compared to regex-only scanners.

Is it safe to use claude --dangerously-skip-permissions with ShipSafe?

ShipSafe's git pre-commit hooks provide a safety net when using --dangerously-skip-permissions. Even if Claude Code writes insecure code in autonomous mode, ShipSafe blocks the commit if it contains hardcoded secrets or critical vulnerabilities. Install hooks with: shipsafe hooks install.

ShipSafe vs Semgrep — Security Scanner Comparison

Semgrep is a well-established open-source static analysis tool used by many enterprises. ShipSafe is a newer security scanner purpose-built for individual developers and small teams using AI coding assistants. Here is an honest comparison.

Feature Comparison

Feature	ShipSafe	Semgrep
JavaScript/TypeScript rules	757 rules	~500 rules
Python rules	200+ rules	400+ rules
Prompt injection detection	7 rules	Not available
Malicious MCP scanning	30 patterns	Not available
Secret detection	174 patterns (built-in)	Via Semgrep Secrets (paid)
Image metadata stripping	Built-in (MetaStrip)	Not available
Installation	npm install -g @shipsafe/cli	pip install semgrep or Docker
MCP server for AI assistants	8 tools	Not available
Git pre-commit hooks	Built-in	Via pre-commit framework
Local-only scanning	Yes, always	Yes (OSS), cloud available (paid)
Custom rules	.shipsafeignore exclusions	Full YAML rule authoring
Enterprise features	Team plan ($49/mo)	Semgrep Cloud (enterprise pricing)
Language support	JS, TS, Python	30+ languages

ShipSafe Strengths

✓More JS/TS rules (757 vs ~500) — deeper coverage for web applications
✓Prompt injection and AI security detection — unique capability
✓Malicious MCP server scanning — protects your AI development environment
✓Image metadata stripping (MetaStrip) — unique capability
✓One-command npm install — no Python or Docker required
✓MCP server integrates directly with Claude, Cursor, Windsurf
✓Built-in git hooks without extra configuration
✓Zero false positives reported on real user projects

Semgrep Strengths

✓Supports 30+ programming languages vs ShipSafe's 3
✓Full custom rule authoring with powerful YAML DSL
✓Mature enterprise features (SSO, role-based access, CI/CD integration)
✓Larger community and more third-party rules
✓Deeper Python coverage (~400 vs ~200 rules)
✓Battle-tested in large enterprise deployments

Key Differentiators

AI Security

ShipSafe is the only scanner with prompt injection detection (7 rules) and malicious MCP server scanning (30 patterns). If you build AI applications, this is critical.

Developer Experience

ShipSafe installs via npm and runs with one command. No Docker, no Python, no configuration files. Semgrep requires pip or Docker and optional pre-commit setup.

Privacy

Both can run locally, but ShipSafe never has a cloud option for source code. Your code stays on your machine, period.

Image Security

ShipSafe's MetaStrip strips GPS coordinates, EXIF data, and camera info from images. No other scanner offers this.

The Verdict

Choose ShipSafe if you are a JavaScript/TypeScript developer using AI coding assistants and want AI-specific security rules with zero configuration. Choose Semgrep if you need multi-language support (30+ languages) or custom rule authoring for an enterprise environment.

Try ShipSafe Free

Install and scan your project in under 60 seconds.

npm install -g @shipsafe/cli

Get Started Free How It Works

Other Comparisons

ShipSafe vs Snyk →ShipSafe vs SonarQube →ShipSafe vs CodeQL →