Files
skillkit/packages/cli/README.md
Rohit Ghumare b28a2801b2 feat: add security scanner for detecting malicious patterns in skills (#50)
* feat: add security scanner for detecting malicious patterns in skills

Add `skillkit scan <path>` command with 46+ detection rules across 6 threat
categories: prompt injection, command injection, data exfiltration, tool abuse,
hardcoded secrets, and unicode steganography.

- 3 analyzers: static pattern matching, SKILL.md manifest validation, secrets detection
- 4 output formats: summary (colored terminal), json, table, sarif (GitHub Code Scanning)
- Auto-scan on `skillkit install` (--no-scan to skip, --force to override)
- Auto-scan on `skillkit publish` (blocks on HIGH+ findings)
- Threat taxonomy with 10 categories and severity levels
- False-positive filtering for placeholders, test files, safe patterns
- Updated README, CLI docs, website commands, features, and fumadocs

* fix: address Devin and CodeRabbit review suggestions for security scanner

- Fix .env variant files (.env.local, .env.production) being skipped by scanner
- Add multiline rule support in StaticAnalyzer for cross-line pattern matching
- Fix PI004/PI013 patterns that contained literal \n (never matched per-line)
- Fix /g flag on CI006 path traversal regex causing intermittent misses
- Fix frontmatter regex to handle Windows CRLF line endings
- Fix allowed-tools parsing to detect multi-line YAML arrays
- Fix snippet redaction order: redact before truncate to prevent secret leaks
- Reset findingCounter per analyze() call for deterministic finding IDs
- Make SARIF artifactLocation.uri relative to skillPath for GitHub Code Scanning
- Use basename() instead of split('/').pop() for cross-platform paths
- Inject package version at build time via tsup define (replaces hardcoded 1.0.0)
- Validate --fail-on and --format CLI options with clear error messages
- Remove unused format/quiet from ScanOptions interface
- Move publish scan after name validation to avoid blocking on invalid skills
- Add excludePatterns for jailbreak detection to reduce false positives
- Add biome suppression for intentional control character regex in UC005
- Use alternation instead of character class for ZWJ in UC001

* fix: address CodeRabbit round 2 review suggestions

- Remove unused --quiet option from scan command
- Update OpenAI API key pattern to detect sk-proj- and sk-admin- prefixes

* fix: address deep review issues in security scanner

- SK001: add negative lookahead to prevent matching Anthropic keys
- static.ts: fix multiline loop hang for non-global regex with filtered matches
- CI005: reduce severity to MEDIUM, expand excludePatterns for template literals
- CI006: reduce severity to MEDIUM, add fileTypes whitelist, exclude markdown/YAML patterns
- PI011: fix literal \n in regex, use $/im for end-of-line matching
- UC004: use \u{...} notation for supplementary codepoint range
- scanner.ts: propagate skipRules to ManifestAnalyzer and SecretsAnalyzer
2026-02-08 12:56:45 +00:00

7.6 KiB

@skillkit/cli

npm version License

Command-line interface for SkillKit - install, manage, translate, and sync skills across 32 AI coding agents.

Installation

npm install -g @skillkit/cli
# or
npm install -g skillkit  # includes CLI

Quick Start

# Get skill recommendations for your project
skillkit recommend

# Install skills from GitHub
skillkit install anthropics/skills

# Translate skills between agents
skillkit translate my-skill --to cursor

# Launch interactive TUI
skillkit ui

All Commands

Skill Management

skillkit install <source>     # Install from GitHub/GitLab/Bitbucket/local
skillkit remove <skills>      # Remove installed skills
skillkit update [skills]      # Update skills from source
skillkit list                 # List installed skills
skillkit enable <skills>      # Enable specific skills
skillkit disable <skills>     # Disable specific skills
skillkit sync                 # Sync to agent config
skillkit read <skills>        # Read skill content

Discovery & Recommendations

skillkit recommend                     # Project-based recommendations
skillkit recommend --search "auth"     # Task-based search
skillkit recommend --category security # Filter by category
skillkit recommend --min-score 80      # Quality threshold

skillkit marketplace                   # Browse skills
skillkit marketplace search "react"    # Search marketplace
skillkit marketplace --tags typescript # Filter by tags
skillkit marketplace refresh           # Refresh index

Translation

skillkit translate <skill> --to <agent>  # Translate single skill
skillkit translate --all --to cursor     # Translate all skills
skillkit translate skill --dry-run       # Preview without writing

Context Management

skillkit context init          # Analyze project, create context
skillkit context show          # Display current context
skillkit context sync --all    # Sync to all detected agents
skillkit context export        # Export context file

Session Memory

skillkit memory status         # View memory status
skillkit memory search "auth"  # Search learnings
skillkit memory list           # List all learnings
skillkit memory compress       # Compress observations
skillkit memory export <id>    # Export as skill
skillkit memory add            # Add manual learning
skillkit memory --global       # Use global scope

Testing & Workflows

skillkit test                  # Run all skill tests
skillkit test ./my-skill       # Test specific skill
skillkit test --tags unit      # Run tagged tests

skillkit workflow list         # List workflows
skillkit workflow run <name>   # Execute workflow
skillkit workflow create       # Create new workflow

skillkit cicd github-action    # Generate GitHub Actions
skillkit cicd gitlab-ci        # Generate GitLab CI
skillkit cicd pre-commit       # Generate pre-commit hook
skillkit cicd init             # Initialize CI/CD templates

Team Collaboration

skillkit team init --name "Team"     # Initialize team
skillkit team share <bundle>         # Share skill bundle
skillkit team import <path>          # Import bundle
skillkit team list                   # List team bundles
skillkit team sync                   # Sync with remote
skillkit team remove <bundle>        # Remove bundle
skillkit team bundle-create          # Create new bundle
skillkit team bundle-export <id>     # Export bundle
skillkit team bundle-list            # List all bundles

Plugin System

skillkit plugin list                 # List installed plugins
skillkit plugin install <name>       # Install plugin
skillkit plugin uninstall <name>     # Uninstall plugin
skillkit plugin enable <name>        # Enable plugin
skillkit plugin disable <name>       # Disable plugin
skillkit plugin info <name>          # Plugin details

Methodologies & Plans

skillkit methodology list            # List methodologies
skillkit methodology load <name>     # Load methodology
skillkit methodology apply <name>    # Apply to project

skillkit plan parse <file>           # Parse plan file
skillkit plan validate <file>        # Validate plan
skillkit plan execute <file>         # Execute plan
skillkit plan status                 # Plan execution status

Hooks & Automation

skillkit hook list                   # List registered hooks
skillkit hook register <event>       # Register new hook
skillkit hook trigger <event>        # Trigger hook manually
skillkit hook enable <id>            # Enable hook
skillkit hook disable <id>           # Disable hook

Agent Commands

skillkit command generate <agent>    # Generate agent-native commands
skillkit command list <agent>        # List available commands

Security Scanning

skillkit scan <path>                  # Scan skill for vulnerabilities
skillkit scan <path> --format json    # Output as JSON
skillkit scan <path> --format sarif   # SARIF for GitHub Code Scanning
skillkit scan <path> --fail-on high   # Exit code 1 if HIGH+ findings
skillkit scan <path> --skip-rules UC001,UC002  # Skip specific rules

Detects: prompt injection, command injection, data exfiltration, tool abuse, hardcoded secrets, unicode steganography.

Skills are automatically scanned during install (use --no-scan to skip) and publish.

Utilities

skillkit init                  # Initialize in project
skillkit init --agent cursor   # Initialize for specific agent
skillkit validate ./skill      # Validate skill format
skillkit create my-skill       # Create new skill
skillkit settings              # View all settings
skillkit settings --set key=value  # Update setting

Install Options

skillkit install owner/repo              # GitHub repository
skillkit install gitlab:owner/repo       # GitLab repository
skillkit install ./local/path            # Local directory

# Options
--list                    # List available skills without installing
--skills=pdf,xlsx         # Install specific skills
--all                     # Install all discovered skills
--yes                     # Skip confirmation prompts
--global                  # Install globally
--force                   # Overwrite existing
--no-scan                 # Skip security scan
--agent=cursor,windsurf   # Install to specific agents

Programmatic Usage

import {
  installCommand,
  listCommand,
  syncCommand,
  translateCommand,
  recommendCommand,
} from '@skillkit/cli';

// Install skills programmatically
await installCommand('anthropics/skills', {
  agent: ['claude-code', 'cursor'],
  yes: true,
});

// List installed skills
const skills = await listCommand({ json: true });

// Sync to agent
await syncCommand({ all: true });

// Translate skill
await translateCommand('my-skill', {
  to: 'cursor',
  dryRun: false,
});

// Get recommendations
const recs = await recommendCommand({
  path: './my-project',
  minScore: 70,
});

CI/CD Usage

# GitHub Actions example
- name: Setup skills
  run: |
    npx skillkit install owner/skills --skills=lint,test --yes
    npx skillkit sync --yes

Supported Agents

Agent Format
Claude Code SKILL.md
Cursor MDC (.mdc)
Codex SKILL.md
Gemini CLI SKILL.md
Windsurf Markdown
GitHub Copilot Markdown
+ 26 more SKILL.md

Documentation

Full documentation: https://github.com/rohitg00/skillkit

License

Apache-2.0