Agent Skills
› H-mmer/pentest-agents
› surface
surface
GitHub用于对目标进行攻击面排名。通过调用recon-ranker代理,结合侦察数据和脑数据,依据漏洞利用经济学将资产分为P1/P2/Kill等级,并建议后续渗透测试步骤。
Trigger Scenarios
用户请求分析目标的攻击面
输入包含/surface命令及目标域名
Install
npx skills add H-mmer/pentest-agents --skill surface -g -y
SKILL.md
Frontmatter
{
"name": "surface",
"description": "Show ranked attack surface for a target. Invokes recon-ranker agent. Usage: \/surface target.com",
"disable-model-invocation": false
}
Rank attack surface for: $ARGUMENTS
- Verify recon data exists in recon/ directory. If not, suggest /recon first.
- Read brain data for this target.
- Launch
recon-rankeragent: "Rank the attack surface for $ARGUMENTS. Read recon/ for discovery data and brain for tested endpoints. Output P1/P2/Kill ranking." - Show the ranking to the user.
- Suggest:
/hunt $ARGUMENTSto start testing P1 targets.
Top-Tier Surface Ranking
Rank by exploit economics.
P1 requires at least two of:
- crown-jewel function: auth, billing, admin, tenant data, integrations, uploads, exports, webhooks, AI/tool execution
- weak boundary: cross-tenant IDs, mixed roles, public/private transition, OAuth callback, parser boundary, file ingestion
- novelty: new asset, changed JS, low hacktivity coverage, unusual vendor or beta endpoint
- proof path: two-account test, clear callback, readable response, browser-verifiable sink, local PoC
Kill or P3 assets that are static marketing pages, hardened vendor panels with no program-owned data, or endpoints already exhausted with strong evidence. Every P1 must include the best first vuln class and first request to try.
Version History
- 41d49b6 Current 2026-07-24 11:57


