Skip to content
Security
Command

/scan-web

Run the full web SAST pipeline (phases 01-06) against this repository

From plugin
vantage
46 skills28 agents6 commands
Install
> /plugin marketplace add tinoimammp/vantage-security-agent
> /plugin install vantage@vantage

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/scan-web

Context preview

What this command does when you run it.

Run the full web SAST pipeline (phases 01-06) against this repository

Command definition

scan-web.md
description: Run the full web SAST pipeline (phases 01-06) against this repository
argument-hint: "[repository path, defaults to current working directory]"
allowed-tools: Task, Read, Glob, Write

Run the complete **web** `vantage` pipeline against `$ARGUMENTS` (default: current working directory), phases 01 through 06, honoring the gates in `${CLAUDE_PLUGIN_ROOT}/workflow/orchestration.md`.

Read `${CLAUDE_PLUGIN_ROOT}/START-HERE.md` and `${CLAUDE_PLUGIN_ROOT}/workflow/orchestration.md` first if you have not already this session.

1. If `./.vantage/artifacts/recon/scope.json` doesn't exist, copy the plugin asset `${CLAUDE_PLUGIN_ROOT}/artifacts/recon/scope.json.template` → `./.vantage/artifacts/recon/scope.json`, filling in placeholders with the current system timestamp and repository path. Never block to ask the user. 2. Set/confirm `platform: "web"` in that `scope.json` — this command always runs the web pipeline regardless of what's already there (if it says `"mobile"`, overwrite it to `"web"` for this run and note that you did so). 3. For each phase, in order, check the phase's gate is satisfied (per `${CLAUDE_PLUGIN_ROOT}/workflow/orchestration.md`) — if not, stop and report why — then dispatch via Task:

  • **01 Recon** → `recon-agent`
  • **02 Mapping** → `mapper-agent`
  • **03 Testing** → dispatch all 10 as **parallel Task calls in the same

turn**, each writing its own `raw-findings.<agent-name>.json`: `auth-agent`, `authorization-agent`, `api-agent`, `sqli-agent`, `xss-agent`, `upload-agent`, `business-logic-agent`, `injection-agent`, `dependency-agent`, `secrets-agent`

  • **04 Validation** → `validator-agent` (merges all `raw-findings.*.json` first)
  • **05 PoC** → `poc-agent` (only if ≥1 `validated:true` finding)
  • **06 Reporting** → `report-agent`

4. Append each phase's result to `./.vantage/artifacts/run-log.md`.

Stop and summarize if a phase produces zero actionable output (see Failure & Empty Handling in `${CLAUDE_PLUGIN_ROOT}/workflow/orchestration.md`) — do not fabricate findings.

When done, report the final artifact path — `./.vantage/artifacts/reports/report.md` — and remind the user that `/vantage:fix-issue <id>` or `/vantage:fix` can apply code-level fixes for the validated findings.

Read more
Ships withvantage

AI SAST framework for web & mobile apps, shipped as a Claude Code plugin. Agents read your source code and produce a validated, evidence-backed vulnerability report — no running the app, no network requests.

Get the whole plugin

Other commands on vantage.