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 vigilantshield/Claude-HunterKit --skill ai-19-adversarial-mlgit clone --depth 1 https://github.com/vigilantshield/Claude-HunterKitWrote 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/vigilantshield/claude-hunterkit/ai-19-adversarial-ml)<a href="https://agentmods.dev/skills/vigilantshield/claude-hunterkit/ai-19-adversarial-ml"><img src="https://agentmods.dev/badge/skills/vigilantshield/claude-hunterkit/ai-19-adversarial-ml/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/vigilantshield/claude-hunterkit/ai-19-adversarial-ml"><img src="https://agentmods.dev/badge/skills/vigilantshield/claude-hunterkit/ai-19-adversarial-ml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.00366 |
| Opus 5 | $0.00015 | $0.00183 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade C, and why
ai-19-adversarial-ml scanned grade C 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 10d 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
1. Bypass safety filter with adversarial text The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 10d ago First seen · 55 lines · 31 tokens per session scan C 236e2b55300d
ai-19-adversarial-ml is a skill published in the GitHub repository vigilantshield/Claude-HunterKit (5 stars, last pushed 1mo ago), with no licence file. It adds 31 tokens to every session and 366 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pwnote-engagement-file
Create or validate a pwnote engagement import/export JSON file. Use when the user wants to generate, edit, or verify a pwnote engagement file for data transfer between pwnote instances. The file bundles an entire pentest engagement — metadata, notebook documents, code/host/credential blocks, findings with…
pwnote-cve-research
Use whenever the user is doing vulnerability research aimed at a CVE/advisory — tracking a responsible disclosure timeline, drafting a vendor notification, requesting a CVE ID from MITRE or a CNA, writing a public security advisory, or mapping a finding to a CWE. Trigger on "CVE", "CNA", "MITRE", "advisory"…
pwnote-offsec-osai
Use whenever the user is working on Offsec's OSAI / AI Red Teaming certification track, or on AI/LLM/agentic security engagements generally — prompt injection findings, tool-use abuse, agent trajectory documentation, or writing up AI-specific security findings that don't map cleanly to traditional CVSS. Trigger on…
pwnote-hackthebox
Use whenever the user is working a HackTheBox (HTB) machine or challenge — structuring recon/foothold/privesc notes, building an enumeration checklist, tracking a multi-hop attack path, or writing a writeup (respecting HTB's retirement rules before publishing). Trigger on "HTB", "HackTheBox box", "pwn this machine"…
pwnote-offsec-pen200
Use whenever the user is working on Offsec's PEN-200 course/OSCP — PWK lab notes, exam report drafting, screenshot/evidence discipline, or exam flag handling. Trigger on "OSCP", "PEN-200", "PWK", "OSCP exam report", or "proof.txt", even without the word "skill".
pwnote-offsec-web300
Use whenever the user is working on Offsec's WEB-300 course/OSWE — whitebox source code review methodology, exploit chain documentation, PoC scripting, or OSWE exam report writing. Trigger on "OSWE", "WEB-300", "whitebox", "source code review" in a pentest context, or "exploit chain", even without the word "skill".