The wedge
AI pentest: audit your app without sending the code away.
What an AI pentest is, what it is not, and which kit mode to open for a site, a SaaS, or MCP agents.
Read the guide →Security audit kit
Eight modes. One article each.
You do not pick an internal mode. You name the project — site, SaaS, MCP — and the depth. Each guide says what the squad does, what it refuses, and how to launch.
01-express · 30–45 min
Website security audit: Express mode, a first signal.
When to open Express, what it covers, and why an Express at confidence 5 is a fault.
Read the guide →02-complet-web · 1 day
Web pentest: Full mode, for a site or an app.
Pipeline of a full web audit: what runs, what stays Untested without an account, and when to switch to SaaS.
Read the guide →03-complet-saas · 1–2 days
SaaS audit: isolation first, not headers.
Two-tenant rule, pipeline 00–11, multi-tenant specialist. This is not SSPM (locking down Slack): it is auditing the SaaS YOU build.
Read the guide →04-agents-mcp · 4–8 h
MCP security: audit the tools, not just the UI.
Who may call which tool, a tool + another tenant’s id, exposed prompts and .env, third-party marketplace.
Read the guide →05-delta · 2–6 h
Re-audit: what moved after the fixes.
Snapshot before any new collection, re-check of open findings, no classes outside the baseline.
Read the guide →06-continuous · 30–90 min / run
Periodic guardrail: Continuous mode.
Without a baseline, this is the wrong mode. OpenRouter key on every run. Short QA only if a Confirmed is born.
Read the guide →07-redteam-leger · 1–3 days
Light red team: active, authorized, no weapon.
Four mandate clauses, what “light” allows, and why “it’s my site” in chat is not enough.
Read the guide →08-rapport-board · 1–3 h
Board report: facts already held, nothing else.
Hard gate: qa.passed=true, sign-off present, no finding newer than QA. Otherwise stop.
Read the guide →