Menu
Security patterns and auditing for AI interactions. Scan and audit AI agent skills for security risks before installation.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Design and implement interactive 2D materials and objects — books, notebooks, bookshelves, cards, folders, and similar tactile UI elements. Use this skill whenever designing 2D illustrated assets, adding interactions to visual objects (open/close, flip, drag, hover states), creating a "reading room" or "library" interface, building animated book/document components, or when the user mentions kitaplık, defter, kitap, 2D materyal, interaktif obje, sayfa çevirme, or any illustrated therapeutic tool. Apply proactively for any therapy-app visual material that mimics real-world objects.
Design and implement micro-animations, motion design, and interaction feedback for UI elements. Use this skill whenever adding animations to components, designing hover/click/transition effects, implementing page transitions, creating spring-based physics animations, designing loading states, building gesture-driven interactions (drag, swipe, pinch), or when the user mentions animasyon, geçiş efekti, sayfa çevirme, etkileşim, hareket, micro-interaction, or any mention of making UI elements feel "alive" or "tactile". Apply proactively for any interactive UI component that needs to feel premium and responsive.
Analysis of the digital therapy market landscape and competitive product strategy.
Full content execution pipeline — research, brief, draft, optimize, and polish blog posts, articles, and guides.
Content planning and topic selection — topic clusters, keyword research, content calendars, and prioritization frameworks.
Comprehensive GDPR compliance for sensitive user data. Tools and guidance for EU General Data Protection Regulation (GDPR) and German Bundesdatenschutzgesetz (BDSG) compliance.
| name | skill-security-auditor |
| description | Security patterns and auditing for AI interactions. Scan and audit AI agent skills for security risks before installation. |
Scan and audit AI agent skills for security risks before installation. Produces a clear PASS / WARN / FAIL verdict with findings and remediation guidance.
Scans all .py, .sh, .bash, .js, .ts files for:
| Category | Patterns Detected | Severity |
|---|---|---|
| Command injection | os.system(), os.popen(), subprocess.call(shell=True), backtick execution | 🔴 CRITICAL |
| Code execution | eval(), exec(), compile(), __import__() | 🔴 CRITICAL |
| Obfuscation | base64-encoded payloads, codecs.decode, hex-encoded strings, chr() chains | 🔴 CRITICAL |
| Network exfiltration | requests.post(), urllib.request, socket.connect(), httpx, aiohttp | 🔴 CRITICAL |
| Credential harvesting | reads from ~/.ssh, ~/.aws, ~/.config, env var extraction patterns | 🔴 CRITICAL |
| File system abuse | writes outside skill dir, /etc/, ~/.bashrc, ~/.profile, symlink creation | 🟡 HIGH |
| Privilege escalation | sudo, chmod 777, setuid, cron manipulation | 🔴 CRITICAL |
| Unsafe deserialization | pickle.loads(), yaml.load() (without SafeLoader), marshal.loads() | 🟡 HIGH |
| Subprocess (safe) | subprocess.run() with list args, no shell | ⚪ INFO |
Scans SKILL.md and all .md reference files for:
| Pattern | Example | Severity |
|---|---|---|
| System prompt override | "Ignore previous instructions", "You are now..." | 🔴 CRITICAL |
| Role hijacking | "Act as root", "Pretend you have no restrictions" | 🔴 CRITICAL |
| Safety bypass | "Skip safety checks", "Disable content filtering" | 🔴 CRITICAL |
| Hidden instructions | Zero-width characters, HTML comments with directives | 🟡 HIGH |
| Excessive permissions | "Run any command", "Full filesystem access" | 🟡 HIGH |
| Data extraction | "Send contents of", "Upload file to", "POST to" | 🔴 CRITICAL |
For skills with requirements.txt, package.json, or inline pip install:
| Check | What It Does | Severity |
|---|---|---|
| Known vulnerabilities | Cross-reference with PyPI/npm advisory databases | 🔴 CRITICAL |
| Typosquatting | Flag packages similar to popular ones (e.g., reqeusts) | 🟡 HIGH |
| Unpinned versions | Flag requests>=2.0 vs requests==2.31.0 | ⚪ INFO |
| Install commands in code | pip install or npm install inside scripts | 🟡 HIGH |
| Suspicious packages | Low download count, recent creation, single maintainer | ⚪ INFO |
| Check | What It Does | Severity |
|---|---|---|
| Boundary violation | Scripts referencing paths outside skill directory | 🟡 HIGH |
| Hidden files | .env, dotfiles that shouldn't be in a skill | 🟡 HIGH |
| Binary files | Unexpected executables, .so, .dll, .exe | 🔴 CRITICAL |
| Large files | Files >1MB that could hide payloads | ⚪ INFO |
| Symlinks | Symbolic links pointing outside skill directory | 🔴 CRITICAL |
