fullscan

Agent Skills › H-mmer/pentest-agents › fullscan

fullscan

GitHub

执行全量安全评估，通过多阶段协调智能体跳过已知耗尽区域并复用上下文。新增最高标准，要求覆盖核心资产、记录正负结果、关联低危漏洞以形成攻击链，并确保最终报告包含确认发现及残留风险分析。

providers/codex/.agents/skills/fullscan/SKILL.md H-mmer/pentest-agents

Trigger Scenarios

用户请求全面的安全审计需要执行跨阶段的自动化渗透测试

Install

npx skills add H-mmer/pentest-agents --skill fullscan -g -y

More Options

Non-standard path

npx skills add https://github.com/H-mmer/pentest-agents/tree/main/providers/codex/.agents/skills/fullscan -g -y

Use without installing

npx skills use H-mmer/pentest-agents@fullscan

指定 Agent (Claude Code)

npx skills add H-mmer/pentest-agents --skill fullscan -a claude-code -g -y

安装 repo 全部 skill

npx skills add H-mmer/pentest-agents --all -g -y

预览 repo 内 skill

npx skills add H-mmer/pentest-agents --list

SKILL.md

Frontmatter

{
    "name": "fullscan",
    "description": "Full security assessment with brain coordination. Multi-phase, skips known-exhausted areas, builds on prior knowledge."
}

ALL agents dispatched by this command MUST use in the subagent dispatch tool call.

Full security assessment on: $ARGUMENTS

Phase 0: Brain Briefing

uv run python3 ../../tools/brain.py init (if first run)
uv run python3 ../../tools/brain.py brief $ARGUMENTS
uv run python3 ../../tools/scope_check.py $ARGUMENTS

Phase 1: Recon (skip already-discovered assets)

Launch recon agent with brain context. Focus on discovering NEW subdomains and services beyond what's already known.

Phase 2: Scanning (skip exhausted areas)

Launch IN PARALLEL, each with brain context about what's been scanned before:

vuln-scanner — skip known false positives, focus new hosts
config-auditor — check if previously noted misconfigs are fixed
js-analyzer — focus on new/changed JS files

Record all results to the brain after each agent returns.

Phase 3: Targeted Testing (brain-guided)

Based on Phase 2 + brain knowledge, selectively launch ONLY agents targeting UNTESTED or ACTIVE vectors:

xss-hunter ONLY on endpoints not marked exhausted
api-audit ONLY on newly discovered or untested endpoints
auth-tester ONLY if new auth flows found

Record all results to the brain.

Phase 4: Reporting

uv run python3 ../../tools/dedup_findings.py --scan-dir scans/ --db findings.json --stats
uv run python3 ../../tools/brain.py status
Launch poc-builder for each confirmed finding
Launch report-writer with full brain context
uv run python3 ../../tools/brain.py log "Full scan completed on $ARGUMENTS"

Top-Tier Fullscan Standard

A full scan must leave a defensible coverage ledger.

Start with the crown jewels: auth, tenant data, billing, admin, integrations, uploads, webhooks, exports, AI/tool surfaces, and source/repo exposure.
For each phase, record both positives and negatives. "Scanned" is invalid unless it names tools, targets, timestamps, and skipped areas.
Do not let scanner output dominate. Use scanners to find leads, then spend human-grade effort on state changes, authorization boundaries, and parser differentials.
Before reporting, run /correlate or /chain on all confirmed and partial findings. Single low bugs should not escape the scan if a plausible chain remains.
Final output must contain: confirmed findings, killed false positives, exhausted high-value paths, untested residual risk, and the next best command.