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 hypnguyen1209/offensive-claude --skill privesc-windowsgit clone --depth 1 https://github.com/hypnguyen1209/offensive-claudeWrote 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/hypnguyen1209/offensive-claude/privesc-windows)<a href="https://agentmods.dev/skills/hypnguyen1209/offensive-claude/privesc-windows"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/privesc-windows/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/hypnguyen1209/offensive-claude/privesc-windows"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/privesc-windows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 YARA Match · line 7 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high YARA Match · line 7 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high YARA Match · line 7 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00081 | $0.03183 |
| Opus 5 | $0.00041 | $0.01591 |
| Sonnet 5 | $0.00016 | $0.00637 |
| Haiku 4.5 | $0.00008 | $0.00318 |
Grade A, and why
privesc-windows 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Privilege Escalation
When to Activate
- Gained an initial shell / foothold on Windows and need to reach Administrator or NT AUTHORITY\SYSTEM
- Shell runs as a service account (IIS APPPOOL, MSSQL, Local/Network Service) holding
SeImpersonatePrivilege - Standard-user → admin via UAC bypass (medium → high integrity) on a local-admin-group member
- Service / DLL / scheduled-task misconfiguration hunting on the host
- Kernel EoP via an unpatched local CVE or Bring-Your-Own-Vulnerable-Driver (admin → kernel/PPL)
- Privileged token-right abuse (
SeBackup/SeRestore/SeTakeOwnership/SeLoadDriver/SeDebug) - Local credential harvesting (LSASS, SAM/SYSTEM, DPAPI) to fuel lateral movement
Technique Map
| Technique | ATT&CK | CWE | Reference | Script |
|---|---|---|---|---|
| Automated enumeration (winPEAS/Seatbelt/PrivescCheck) | T1082, T1518 | CWE-1188 | references/enumeration-triage.md | scripts/win_privesc_triage.ps1 |
| Token-privilege triage + FullPowers recovery | T1134.001 | CWE-269 | references/enumeration-triage.md | scripts/win_privesc_triage.ps1 |
| SeImpersonate Potato (GodPotato/SigmaPotato/PrintNotify) | T1134.001, T1134.002 | CWE-269 | references/token-impersonation-potatoes.md | scripts/check_potato.py |
| Named-pipe / token impersonation primitives | T1134.001 | CWE-269 | references/token-impersonation-potatoes.md | scripts/check_potato.py |
| Unquoted service path | T1574.009 | CWE-428 | references/service-dll-hijacking.md | scripts/service_hijack_audit.ps1 |
| Weak service ACL / SERVICE_CHANGE_CONFIG | T1543.003 | CWE-732 | references/service-dll-hijacking.md | scripts/service_hijack_audit.ps1 |
| DLL / phantom DLL hijack (CVE-2025-1729, CVE-2024-28827) | T1574.001, T1574.010 | CWE-427 | references/service-dll-hijacking.md | scripts/service_hijack_audit.ps1 |
| UAC bypass — fodhelper/computerdefaults/eventvwr | T1548.002 | CWE-269 | references/uac-bypass.md | scripts/uac_bypass.ps1 |
| UAC bypass — ICMLuaUtil / IEditionUpgradeManager COM | T1548.002 | CWE-269 | references/uac-bypass.md | scripts/uac_bypass.ps1 |
| AlwaysInstallElevated MSI | T1548.002 | CWE-250 | references/uac-bypass.md | scripts/uac_bypass.ps1 |
| Kernel EoP CVE (CLFS CVE-2025-29824/32701; CVE-2025-62215) | T1068 | CWE-416, CWE-362 | references/kernel-byovd.md | scripts/byovd_loader.c |
| BYOVD admin→kernel / EDR-blind (CVE-2025-7771, EDRSandblast) | T1068, T1562.001 | CWE-782 | references/kernel-byovd.md | scripts/byovd_loader.c |
| Privileged token rights (SeBackup/SeRestore/SeLoadDriver/SeDebug) | T1134, T1068 | CWE-269 | references/kernel-byovd.md | scripts/byovd_loader.c |
| LSASS dump (comsvcs / PssCaptureSnapshot / nanodump) | T1003.001 | CWE-522 | references/credential-harvesting.md | - |
| SAM/SYSTEM + VSS offline secretsdump | T1003.002 | CWE-522 | references/credential-harvesting.md | - |
| DPAPI / credential vault / browser secrets | T1555.004, T1555.003 | CWE-522 | references/credential-harvesting.md | - |
What ships with it
11 files 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.
- references/credential-harvesting.md 7.7 KB
- references/enumeration-triage.md 8.2 KB
- references/kernel-byovd.md 9.1 KB
- references/service-dll-hijacking.md 7.7 KB
- references/token-impersonation-potatoes.md 7.8 KB
- references/uac-bypass.md 7.4 KB
- scripts/byovd_loader.c 2.6 KB
- scripts/check_potato.py 6.0 KB runs code
- scripts/service_hijack_audit.ps1 5.4 KB runs code
- scripts/uac_bypass.ps1 5.2 KB runs code
- scripts/win_privesc_triage.ps1 6.9 KB runs code
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.
- 12d ago First seen · 123 lines · 81 tokens per session scan A a11d2912b257
privesc-windows is a skill published in the GitHub repository hypnguyen1209/offensive-claude (360 stars, last pushed 26d ago), licensed MIT. It adds 81 tokens to every session and 3,183 once invoked, about $0.0004 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
bt6-queue-audit
Audit the full pull-request and issue queue of a BT6 research or support repository, classifying readiness, evidence risk, and next action without mutating tracker state.
bt6-issue-steward
Triage and steward issues in BT6 research and support repositories, deciding whether to answer, reproduce, correct evidence, link work, design a feature, route security, implement, or close.
bt6-merge-train
Run an explicitly authorized, conservative BT6 merge train that processes validated pull requests one at a time and reconciles repository, CI, evidence, and issue state after each merge.
bt6-pr-audit
Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security, tests, contracts, and merge readiness.
bt6-provider-review
Audit an external AI/API provider and its integration into a BT6 repository for service reality, independent verification, trust boundaries, secret handling, API/model correctness, completeness, claim traceability, and merge readiness.
xiaohongshu-search-full
Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares). Supports all page filter options: sort order (general, latest, most liked, most commented…