Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ayalaphiscan/web-security-guard --skill autenticazione-sicuragit clone --depth 1 https://github.com/ayalaphiscan/web-security-guardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ayalaphiscan/web-security-guard/autenticazione-sicura)<a href="https://agentmods.dev/skills/ayalaphiscan/web-security-guard/autenticazione-sicura"><img src="https://agentmods.dev/badge/skills/ayalaphiscan/web-security-guard/autenticazione-sicura/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ayalaphiscan/web-security-guard/autenticazione-sicura"><img src="https://agentmods.dev/badge/skills/ayalaphiscan/web-security-guard/autenticazione-sicura.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00152 | $0.01456 |
| Opus 5 | $0.00076 | $0.00728 |
| Sonnet 5 | $0.00030 | $0.00291 |
| Haiku 4.5 | $0.00015 | $0.00146 |
Grade A, and why
autenticazione-sicura scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autenticazione Sicura · Secure Authentication
🇮🇹 Versione italiana qui sotto · 🇬🇧 English version below
Quando un sito/app prevede account utente, implementare l'autenticazione secondo queste regole. Se l'utente non specifica i dettagli, proporre di default: password + verifica email con codice + 2FA opzionale.
Password
- Hash con Argon2id (preferito) o bcrypt (cost ≥ 12). MAI MD5/SHA1/SHA256 semplice, mai password in chiaro.
- Lunghezza minima 8-12 caratteri; verificare contro liste di password compromesse se possibile.
- Rate limiting sul login: max ~5 tentativi per account/IP in 15 minuti, poi blocco temporaneo crescente. Risposta identica per "utente inesistente" e "password errata".
Verifica email con codice (OTP)
- Codice numerico a 6 cifre generato con CSPRNG (
crypto.randomInt,secrets.randbelow), MAIMath.random(). - Validità 10 minuti, monouso, max 5 tentativi di inserimento, poi invalidare e rigenerare.
- Salvare nel DB solo l'hash del codice, con scadenza. Rate limiting sull'invio (max 1 ogni 60s, 5/ora per indirizzo).
- Stesso schema per: conferma registrazione, reset password, conferma di azioni sensibili (cambio email, cambio IBAN, cancellazione account).
2FA / doppio fattore
Offrire in ordine di preferenza:
- Passkey / chiavi di sicurezza (WebAuthn/FIDO2) — resistenti al phishing. Librerie:
@simplewebauthn/server(Node),webauthn(Python). - TOTP (Google Authenticator ecc.) — segreto generato server-side, mostrato via QR, verificato con finestra ±1 step. Librerie:
otplib,pyotp. - Codice via email — minimo accettabile; SMS solo se richiesto esplicitamente.
Regole:
- Alla attivazione del 2FA generare 10 codici di recupero monouso (mostrati una sola volta, salvati hashati).
- Richiedere il 2FA a ogni login da dispositivo nuovo e per azioni sensibili (step-up).
- Disattivazione 2FA solo con ri-autenticazione completa.
Sessioni e token
- Vedi skill hardening-siti per i cookie. In più: invalidare tutte le sessioni al cambio password; lista "dispositivi connessi" con revoca.
- Se si usano JWT: scadenza breve (15 min) + refresh token revocabile salvato server-side; algoritmo fissato (no
alg: none).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 83 lines · 152 tokens per session scan A cba0ac5165e4
autenticazione-sicura is a skill published in the GitHub repository ayalaphiscan/web-security-guard (4 stars, last pushed 3mo ago), licensed MIT. It adds 152 tokens to every session and 1,456 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
prowler-mcp
Creates MCP tools for Prowler MCP Server. Covers BaseTool pattern, model design, and API client usage. Trigger: When working in mcpserver/ on tools (BaseTool), models (MinimalSerializerMixin/fromapiresponse), or API client patterns.
add-cloud-flow
Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…
octopus-architecture
Review system architecture, simplify boundaries, or compare interface designs from repository evidence.
list-connections
Lists Power Platform connections in the current environment. Use when you need a connection ID before adding a connector to a code app.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.