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 Miosa-osa/OSA --skill offensive-vuln-classesgit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/offensive-vuln-classes)<a href="https://agentmods.dev/skills/miosa-osa/osa/offensive-vuln-classes"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-vuln-classes/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/miosa-osa/osa/offensive-vuln-classes"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-vuln-classes.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 | $0.00069 | $0.07066 |
| Opus 5.5 | $0.00028 | $0.02826 |
| Sonnet 5.5 | $0.00014 | $0.01413 |
| Haiku 4.5 | $0.00007 | $0.00707 |
Grade A, and why
offensive-vuln-classes 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 1mo 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- **The Impact**: Remote code execution via a crafted web page with no user interaction beyond visiting the page. By placing a fake object in the freed memory location, the attacker could hijack control flow and execute Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Week 1: Vulnerability Classes with Real-World Examples
Metadata
- Skill Name: vulnerability-classes
- Folder: offensive-vuln-classes
- Source: https://github.com/SnailSploit/offensive-checklist/blob/main/1-vulnerability-classes.md
Description
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit dev knowledge.
Trigger Phrases
Use this skill when the conversation involves any of:
vulnerability classes, buffer overflow, use-after-free, UAF, heap overflow, stack overflow, type confusion, integer overflow, format string, memory corruption, CVE case study, exploit development, Day 1-7
Full Methodology
Week 1: Vulnerability Classes with Real-World Examples
Course Overview
created by AnotherOne from @Pwn3rzs Telegram channel.
This document is Week 1 of a multi‑week exploit development course, focusing on core vulnerability classes and real‑world exploitation context.
Next Week we'll focus on using fuzzing to identify new vulnerabilites and in week 3 we'll focus on using patch diffing to find n-days
Day 1: Memory Corruption Fundamentals
- Goal: Understand primary memory corruption vulnerability classes and their real-world impact.
- Activities:
- Reading:
- "The Art of Software Security Assessment" by Mark Dowd, John McDonald, Justin Schuh - Chapter 5: Memory Corruption
- Memory Corruption: Examples, Impact, and 4 Ways to Prevent It
- Online Resources:
- Microsoft Security Research: Memory Safety
- Google Project Zero Blog - Read recent memory corruption findings
- Concepts:
- What is memory corruption and why does it matter?
- Understanding the stack, heap, and their differences
- The lifecycle of memory: allocation → use → deallocation
- Reading:
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.
- 1mo ago First seen · 305 lines · 69 tokens per session scan A baeeaa88052c
offensive-vuln-classes is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 7d ago), licensed Apache-2.0. It adds 69 tokens to every session and 7,066 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
canvas
Fetch Canvas LMS courses and assignments via API token.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
ace-rsi-toolkit
Run ACE (Agentic Context Engineering, Zhang et al. 2025) on an agent the sequential offline way - a Reflector reads each training Trace, a Curator adds the lessons to a playbook of rules the agent reads before every task, and the final playbook is measured on a published Benchmark.
eli5
Explain concepts in very simple terms suitable for a five-year-old.
socratic-quiz
Use this when the user wants to deeply understand something through guided questioning. Trigger phrases include: "quiz me", "help me understand", "Socratic", "teach me", "walk me through with questions", "test my understanding", or when the user asks for an explanation and would benefit more from guided discovery than…