Restructure the entire documentation site following the Diátaxis framework (Learn / How-to / Understand / Reference) with new content across 110 files. ## Information Architecture (M1) - Move all docs to Diátaxis directory structure (learn/, how-to/, understand/, reference/) - Add client-redirects plugin for old URL compatibility - Rewrite sidebar, navbar, and footer to match new IA - Update all internal cross-references ## Homepage + Quickstarts (M2) - Add scenario entry cards to homepage with hand-drawn design - 5 quickstart pages: Claude Code, GitHub Copilot (with copy mode recommendation), Codex, Multiple Tools, Dev Containers, Playground ## Blog + Changelog (M3) - Enable Docusaurus blog plugin with authors.yml - 5 blog posts: 5-min tutorial, managing 50+ skills, skillshare vs vercel/skills comparison, team sharing patterns, write your first skill - Static /changelog page from CHANGELOG.md ## Recipes + Philosophy (M4) - 5 recipe pages: CI/CD validation, enterprise skills, project setup, cross-machine sync, team onboarding - 3 philosophy pages: why-local-first, security-first, sync-modes-explained ## Content Polish - Cross-validate all content against CLI source (19 inaccuracies fixed) - Lowercase "skillshare" throughout (avoid brand conflict with Skillshare Inc.) - Add registry.yaml to file structure and Key Paths docs - Highlight multi-platform git support (GitHub, GitLab, Bitbucket, Gitea, Azure DevOps, AtomGit, Codeberg) - Standardize brew install command - Add AsciinemaPlayer component (cast recordings pending)
3.7 KiB
sidebar_position
| sidebar_position |
|---|
| 2 |
Security-First Design
AI skills are executable instructions. skillshare treats them as untrusted input.
The Threat Model
When you install a skill from GitHub, you're giving an AI tool instructions that will influence code generation, file modifications, and potentially command execution. A malicious skill could:
- Inject prompts that override the AI's safety guidelines
- Exfiltrate data by instructing the AI to send file contents to external URLs
- Execute destructive commands through the AI's shell access
- Steal credentials by accessing environment variables or config files
This is not theoretical. Prompt injection is the #1 security concern in AI tooling.
The Audit Engine
skillshare includes a built-in security scanner (skillshare audit) that checks every installed skill against 15+ detection patterns across 5 severity levels:
| Severity | Examples |
|---|---|
| CRITICAL | Prompt injection, system prompt override |
| HIGH | Data exfiltration URLs, credential access patterns |
| MEDIUM | Destructive commands (rm -rf, DROP TABLE), file system writes |
| LOW | Network requests, external tool invocation |
| INFO | Large file sizes, unusual formatting |
How It Works
The audit engine scans SKILL.md content using pattern matching and heuristics:
# Scan all installed skills
skillshare audit
# JSON output for CI integration
skillshare audit --json
# Scan project skills only
skillshare audit -p
Automatic Blocking
During skillshare install, the audit runs automatically. If a CRITICAL finding is detected, installation is blocked:
CRITICAL: Prompt injection detected in "malicious-skill"
→ Pattern: "ignore previous instructions"
→ Installation blocked. Use --force to override (not recommended).
Defense in Depth
The audit engine is one layer. skillshare's security model includes:
- Audit at install time — catch threats before they reach your AI tools
- Audit on demand — re-scan existing skills as new patterns are added
- Symlink isolation — skills are symlinked, not copied, so the source remains the authority
- Backup before changes —
skillshare backupsnapshots your entire skill library - Trash with TTL — deleted skills go to trash first, not permanent deletion
- Operation logging — every mutating operation is logged to
operations.log(JSONL)
Supply Chain Considerations
The AI skill ecosystem is young. There are no package registries with review processes, no code signing, no dependency resolution. Skills are Markdown files in git repositories.
skillshare's approach:
- Scan everything — even skills from trusted sources
- Block by default — CRITICAL findings prevent installation
- Log everything — audit results are stored for forensic review
- Update patterns — new detection patterns ship with each skillshare release
Configuring Audit Behavior
Set the block threshold in config.yaml to control what severity blocks installation:
# config.yaml
audit:
block_threshold: HIGH # Block on HIGH and CRITICAL (default: CRITICAL)
For per-rule customization, use a separate audit-rules.yaml file (initialized with skillshare audit --init-rules):
# audit-rules.yaml
rules:
- id: network-request-0
enabled: false # Disable this specific rule
- id: my-custom-check
severity: MEDIUM
pattern: "TODO|FIXME"
description: Policy violation — unresolved TODOs