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-windows-privescgit 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-windows-privesc)<a href="https://agentmods.dev/skills/miosa-osa/osa/offensive-windows-privesc"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-windows-privesc/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-windows-privesc"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-windows-privesc.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 | $0.00203 | $0.06128 |
| Opus 5.5 | $0.00081 | $0.02451 |
| Sonnet 5.5 | $0.00041 | $0.01226 |
| Haiku 4.5 | $0.00020 | $0.00613 |
Grade B, and why
offensive-windows-privesc scanned grade B 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
8. Harvest credentials from SAM, DPAPI, LSA secrets, and Credential Manager. 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 — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Privilege Escalation
You have a standard user shell on a Windows target. Your objective is to escalate to NT AUTHORITY\SYSTEM or local Administrator through systematic enumeration and exploitation of misconfigurations, vulnerable services, and unpatched software. This skill provides a structured methodology that moves from passive reconnaissance through increasingly aggressive techniques.
Windows privilege escalation differs fundamentally from Linux. The attack surface centers on services, tokens, the registry, DLL loading mechanics, and the Windows access control model. Master these primitives and you can chain findings from any enumeration tool into a working escalation path.
Quick Workflow
- Run automated enumeration (WinPEAS, PowerUp, Seatbelt) to surface misconfigurations.
- Check current privileges -- SeImpersonate/SeAssignPrimaryToken are immediate wins.
- Enumerate services for unquoted paths, weak DACLs, and writable binaries.
- Check AlwaysInstallElevated registry keys for MSI-based escalation.
- Identify DLL hijacking opportunities in privileged processes.
- Attempt UAC bypass if running as a local admin without elevated context.
- Inspect scheduled tasks, registry autoruns, and writable PATH directories.
- Harvest credentials from SAM, DPAPI, LSA secrets, and Credential Manager.
- Check for PrintNightmare and other unpatched vulnerabilities as a last resort.
Automated Enumeration
Run automated tools first to build a comprehensive picture of the attack surface. Review output methodically -- these tools surface findings you would otherwise miss.
# WinPEAS
.\winPEASx64.exe > C:\Users\Public\winpeas.txt 2>&1
.\winPEASx64.exe servicesinfo # Specific checks only
# PowerUp
Import-Module .\PowerUp.ps1
Invoke-AllChecks | Out-File -FilePath C:\Users\Public\powerup.txt
# SharpUp / Seatbelt / BeRoot
.\SharpUp.exe audit
.\Seatbelt.exe -group=all > C:\Users\Public\seatbelt.txt
.\beRoot.exe
Token Impersonation
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 · 621 lines · 203 tokens per session scan B 1b4405ac0126
offensive-windows-privesc is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 203 tokens to every session and 6,128 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it B with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.