VulnClaw is an AI-driven command-line penetration-testing agent that turns natural-language instructions into an automated workflow for reconnaissance, vulnerability discovery, exploitation, and report generation. It is intended for authorized penetration tests, CTF competitions, security teaching, and red-team exercises, using LLMs and MCP tools. The catalogue contains its specialized skills for security-testing tasks.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Netw0rkNoob/VulnClaw --skill cve-triagegit clone --depth 1 https://github.com/Netw0rkNoob/VulnClawWrote 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/netw0rknoob/vulnclaw/cve-triage)<a href="https://agentmods.dev/skills/netw0rknoob/vulnclaw/cve-triage"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/cve-triage/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/netw0rknoob/vulnclaw/cve-triage"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/cve-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00616 |
| Opus 5 | $0.00022 | $0.00308 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
cve-triage scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- cve-triage — 100% identical, 0 lines differ
- cve-triage — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CVE Triage
Turn version/banner evidence from recon into a prioritized, exploitability-aware
list of CVEs worth verifying. Use this after fingerprinting a service, when a
banner or Server: header reveals a product and version, or whenever the target
exposes software with a known version.
The cve_lookup tool
VulnClaw ships a read-only cve_lookup tool backed by NVD:
- Keyword search —
cve_lookup(query="Apache httpd 2.4.49", limit=5)returns the top CVEs sorted by CVSS, highest first. - CVE-ID detail —
cve_lookup(query="CVE-2021-44228")returns the full record plus best-effort exploit / PoC repositories discovered on GitHub.
It performs no egress to the target and is safe during recon. Without an
NVD_API_KEY it still works (lower rate limit); set one for heavier use.
Workflow
- Extract product + version from recon — service banners,
Serverheaders, JS bundles, login footers, package manifests. A precise version string (OpenSSH 8.2p1,nginx 1.18.0) yields far better matches than a bare name. - Query
cve_lookupwith"<product> <version>". Pull the detail record for any high/critical hit by re-querying itsCVE-ID. - Score & prioritize — see
references/cve-triage-workflow.md. Rank by CVSS, then by exploit availability, then by exposure (is the vulnerable surface actually reachable on this target?). - Confirm version applicability — match the target's version against the
CVE's affected
cperange before claiming it. Banner ≠ proof of vulnerability. - Record findings with the CVE-ID, CVSS, and the evidence that maps this target to it. Mark unconfirmed version-only matches as needs-manual-review, not verified.
Pitfalls
- A keyword match is a hypothesis, not a finding — version ranges and backported patches mean a banner version can be patched in place.
- GitHub "PoC" repos are unverified third-party code; treat as leads, never run blindly against a target.
- Prefer the CVSS base score for triage, but let exploit availability and real exposure override raw score when prioritizing verification effort.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 52 lines · 44 tokens per session scan A 9cf49c8ef992
cve-triage is a skill published in the GitHub repository Netw0rkNoob/VulnClaw (3,299 stars, last pushed 6d ago), licensed MIT. It adds 44 tokens to every session and 616 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
clawmoat
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
minecraft-async
Manage a preinstalled local Minecraft Java client asynchronously for CTF and automation workflows. Use when an agent needs to launch Minecraft in offline mode with alternate usernames, inspect Minecraft logs, focus or type into the X11 game window, send chat or slash commands quickly, or join a multiplayer server by…
sagemath
Run SageMath through an explicit override, a detected environment named sage, or a PATH-resolved command. Use for CTF and cryptography work involving asymmetric cryptography, finite fields, elliptic curves, lattices, polynomial algebra, modular arithmetic, discrete logs, small-root attacks, or PRNG cryptanalysis.
opencrow-crypto-toolbox
Use the best available portable Python runtime and installed crypto tooling for CTF tasks that fit normal Python or CLI cracking rather than SageMath. Prefer a detected ctf environment. Use when an agent needs z3, fpylll, pycryptodome, hashcat, john, or quick FactorDB lookups.
opencrow-reversing-toolbox
Use the best available portable Python runtime and installed reverse-engineering tooling for binary analysis, symbolic execution, disassembly, emulation, and binary patching. Prefer a detected ctf environment. Use when an agent needs angr, claripy, capstone, unicorn, ghidra-headless, radare2, objdump, strace, ltrace…