Claude Code Spec Workflow is a set of Claude Code commands and agents that organizes software work into documented stages for new features and bug fixes. It is for developers who want Claude Code to handle requirements, design, implementation, issue resolution, and verification through repeatable workflows, with the catalogue entries providing the associated commands and agents.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/elementalsouls/Claude-BugHunternpx agentmods add skills/elementalsouls/claude-bughunter/enterprise-vpn-attackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/elementalsouls/claude-bughunter/enterprise-vpn-attack)<a href="https://agentmods.dev/skills/elementalsouls/claude-bughunter/enterprise-vpn-attack"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-bughunter/enterprise-vpn-attack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/elementalsouls/claude-bughunter/enterprise-vpn-attack"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-bughunter/enterprise-vpn-attack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 179 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 186 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 302 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 169 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 247 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00158 | $0.05014 |
| Opus 5 | $0.00079 | $0.02507 |
| Sonnet 5 | $0.00032 | $0.01003 |
| Haiku 4.5 | $0.00016 | $0.00501 |
Grade A, and why
enterprise-vpn-attack scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -skI 'https://target/+CSCOE+/logon.html' | head -10 Copies of this mod
3 near-identical copies found in the catalogue:
- enterprise-vpn-attack — 100% identical, 0 lines differ
- enterprise-vpn-attack — 97% identical, 2 lines differ
- enterprise-vpn-attack — 88% identical, 133 lines differ
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Trigger when recon surfaces:
*.<client>.example/+CSCOE+/logon.htmlor similar+CSCOE+paths → Cisco ASA / AnyConnectintranet.*/vpn.*/connect.*/webvpn.*/wc.*/remote.*subdomains- Port 443 returning login pages with
Server: Apacheor banner like "AnyConnect", "FortiGate", "NetScaler", "GlobalProtect", "Pulse", "Ivanti" - TCP 8443 / 4443 / 10443 / 8888 (common VPN web-mgmt ports)
- HTTP responses with
Set-Cookie: webvpn=(Cisco) /SVPNCOOKIE=(Fortinet) /NSC_AAA=(Citrix) /DSAuthSession=(Pulse) /BIGipServer*(F5)
DO NOT use for:
- Internal lateral-movement post-foothold (out of scope per user's boundary)
- VPN client-side bugs (different attack class)
- IPsec / L2TP / OpenVPN (different protocols, not SSL VPN web stack)
Vendor identification (fingerprinting)
Cisco ASA / AnyConnect
curl -skI 'https://target/+CSCOE+/logon.html' | head -10
# Look for: Set-Cookie: webvpn=; X-Frame-Options: SAMEORIGIN; CSP: ... block-all-mixed-content
# Login page contains: "AnyConnect", "CSCOE", "logon.html"
ASA version: not banner-disclosed in modern builds; need to derive from JS file paths or test specific paths.
# Path-based version hints (older builds leaked builds in URLs)
curl -sk 'https://target/+CSCOE+/sdesktop/scan-finalize?path=test'
curl -sk 'https://target/+CSCOE+/saml/sp/metadata' # 200 = SAML auth enabled
curl -sk 'https://target/CSCOSSLC/config-auth' # AnyConnect handshake endpoint
Fortinet FortiGate / FortiOS
curl -skI 'https://target/remote/login' | head -10
# Look for: Set-Cookie: SVPNCOOKIE=, Server header missing or "xxxxxxxx-xxxxx"
# Login page contains: "FortiGate", "Fortinet", "SSL-VPN"
Version: /remote/info sometimes leaks (older), or /login?username= 302 response
Citrix NetScaler / ADC / Gateway
curl -skI 'https://target/' | head -10
# Look for: Set-Cookie: NSC_AAA=, Set-Cookie: NSC_USER=, Server: NetScaler
# Login page contains: "NetScaler", "Citrix Gateway"
# Version banner
curl -sk 'https://target/vpn/index.html' | grep -oE 'NetScaler/[0-9.]+|NS[0-9.]+'
curl -sk 'https://target/menu/neo' # 200 if vulnerable to CVE-2019-19781 era
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 357 lines · 158 tokens per session scan A 3efcc1022cf2
enterprise-vpn-attack is a skill published in the GitHub repository elementalsouls/Claude-BugHunter (4,298 stars, last pushed 5d ago), licensed MIT. It adds 158 tokens to every session and 5,014 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
bug-bounty
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload…
web2-vuln-classes
Complete reference for 26 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10…
credential-attack
Password spray methodology for bug bounty — when to do it vs web-vuln hunting, the wordlist-gen + breach-check + osint-employees + spray pipeline, mode selection (http-form / oauth / o365 / okta), rate-limit + lockout tactics, BBP legal guardrails, success detection, and the spray → authenticated /hunt chain pattern.…
mobile-pentest
Mobile app pentest for bug bounty (Android APK + iOS IPA) — runtime-first workflow: install app, proxy through Burp/mitmproxy, drive the UI, capture packets, then test the API exactly like a web target; escalate to decompile (apktool/jadx) and Frida/objection only when traffic is SSL-pinned, encrypted, or absent.…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
graphql-audit
GraphQL security hunting — introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass. Covers graphw00f fingerprinting, gqlmap, graphql-cop, and inql. Use when a target exposes a…