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 UnboundCompute/security-agent-skills --skill auditing-windows-token-and-privilege-abusegit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/auditing-windows-token-and-privilege-abuse)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-windows-token-and-privilege-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-windows-token-and-privilege-abuse/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/unboundcompute/security-agent-skills/auditing-windows-token-and-privilege-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-windows-token-and-privilege-abuse.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 | $0.00161 | $0.02098 |
| Opus 5.5 | $0.00064 | $0.00839 |
| Sonnet 5.5 | $0.00032 | $0.00420 |
| Haiku 4.5 | $0.00016 | $0.00210 |
Grade A, and why
auditing-windows-token-and-privilege-abuse 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 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.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing Windows token and privilege abuse: when a held privilege is a ladder
A Windows access token carries the privileges a process may exercise, and a handful of them are equivalent to full control of the host even when the account is not an administrator. A process that can impersonate a client can capture a privileged caller's token and act as that caller. One that holds the privilege to load a driver runs code in the kernel. One that can back up or restore files reads and writes past every access control. One that can take ownership or debug any process reaches into a more privileged context directly. The bug is not that the privilege exists; it is that a lower-privileged foothold holds a privilege, or can obtain a token, whose authorized operation lifts it to a higher context. You audit these by listing the privileges each process holds and each token it can capture, and asking which of them crosses a trust boundary the account was not meant to cross.
When to use
- A service or process runs with a named sensitive privilege enabled that you can enumerate.
- A process accepts connections from privileged callers and can impersonate their tokens.
- A foothold account holds backup, restore, ownership, load-driver, or debug rights on a host you assess.
Scope check
Audit token and privilege abuse only on hosts you own or are authorized to assess, on non-production or a snapshot, using a benign proof that the privileged operation succeeded rather than performing a damaging one. A confirmed abuse reaches a full-control context, so keep every probe within the authorized scope. If you can't name the authorization, stop.
The loop
- Establish which privileges the foothold actually holds and can enable first. For the process or account under assessment, determine the exact set of privileges present in its token and which are enabled or can be enabled, and which privileged tokens it is positioned to capture. This is the false-positive killer: a privilege that is present but not held by the foothold, or an impersonation that only ever receives tokens no more privileged than the account itself, is not an escalation. Name the specific privilege or capturable token before claiming a path.
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 · 138 lines · 161 tokens per session scan A cb5327573457
auditing-windows-token-and-privilege-abuse is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 161 tokens to every session and 2,098 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.