surface — Claude Code command: what it does, how to install
Shows a ranked attack surface for a target from its recon manifest and hunt memory.
MIT ★ 16,193 updated 2026-10-29
/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsoulsWhat surface does
The command reads the manifest at recon/<target>/manifest.json produced by cbh recon and memory of previously tested endpoints. It layers signal from engine/skill_map.py (surface → bug class → skill mapping) and outputs three lists: P1 (start here), P2 (after P1), and Kill List (skip). The deterministic ranking comes from cbh surface <target>.
It prints endpoints with tech stacks, first-seen dates, and suggested test vectors (IDOR, auth bypass, file upload). If no recon data exists, the command prompts you to run /recon target.com first.
What it helps with
- get a prioritized list of endpoints to test for vulnerabilities
- see how attack surface maps to bug classes and skills
- filter out endpoints not worth testing
Example prompts for the agent
- Show attack surface for
example.com - Run
/claude-bughunter:surface api.target.io - List ranked endpoints for
shop.example.org
How to install surface
1Plugin marketplace
/plugin marketplace add elementalsouls/Claude-BugHunter/plugin install claude-bughunter@elementalsouls2Manually: put the files in place
.claude/commands/surface.mdCall it with /surface. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/surface.mdCall it with /prompts:surface. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/surface.prompt.mdManually: put the files in place
.gemini/commands/surface.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about surface
How to install surface in Claude Code?
Run /plugin marketplace add elementalsouls/Claude-BugHunter, then /plugin install claude-bughunter@elementalsouls. The command will be at .claude/commands/surface.md.
What does the surface command do?
It reads the target's recon manifest and hunt memory, ranks endpoints by priority, and outputs three lists: P1 (start here), P2 (after P1), and Kill List (skip).
What does surface need to work?
Run /recon target.com first to create the manifest at recon/<target>/manifest.json. Without it, the command will prompt you to run recon.
Source text
surface.md · MIT
---
name: surface
description: Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com
---
# /surface
View the prioritized attack surface for a target.
## What This Does
1. Reads the recon manifest at `recon/<target>/manifest.json` (produced by `cbh recon`)
— the deterministic ranking comes from `cbh surface <target>`
2. Reads hunt memory for patterns and previously tested endpoints
3. Layers `engine/skill_map.py` (surface → bug-class → skill) + ledger signal on
top of the manifest's `ranked_surface` (P1/P2/Kill)
4. Outputs P1 (start here), P2 (after P1), and Kill List (skip)
> The manifest is the recon→hunt contract — see [`docs/recon-manifest.md`](../docs/recon-manifest.md).
> Run `cbh surface <target>` for the raw deterministic ranking.
## Usage
```
/surface target.com
```
## Prerequisites
Run `/recon target.com` first. If no recon data exists, you'll be prompted to run recon.
## Output
```
ATTACK SURFACE: target.com
═══════════════════════════════════════
Priority 1 (start here):
1. api.target.com/v2/users/{id} — IDOR candidate
Tech: Express + PostgreSQL | First seen 12 days ago
Suggested: numeric ID swap on GET/PUT/DELETE
2. api.target.com/graphql — introspection enabled, 47 mutations
Suggested: field-level auth check on sensitive mutations
Priority 2 (after P1):
1. cdn.target.com:8443/upload — file upload endpoint
Suggested: extension bypass, magic bytes
Kill List (skip):
- static.target.com — CDN only
- docs.target.com — third-party hosted
Memory:
- Pattern from alpha.com (same tech): auth bypass via method override ($800)
- 3 endpoints tested in previous session, 5 remain
```
© Sachin Sharma · MIT · elementalsouls/Claude-BugHunter