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 hunting-windows-service-privilege-escalationgit 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/hunting-windows-service-privilege-escalation)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-windows-service-privilege-escalation"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-windows-service-privilege-escalation/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/hunting-windows-service-privilege-escalation"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-windows-service-privilege-escalation.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 | $0.00174 | $0.02136 |
| Opus 5.5 | $0.00070 | $0.00854 |
| Sonnet 5.5 | $0.00035 | $0.00427 |
| Haiku 4.5 | $0.00017 | $0.00214 |
Grade A, and why
hunting-windows-service-privilege-escalation 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting Windows service privilege escalation: when a standard user decides what SYSTEM runs
A Windows service usually runs as a high-privileged account, often the local system account, and the service manager starts whatever binary the service configuration names. That is safe only if a low-privileged user cannot influence which binary runs or where it is found. When they can, the service becomes an escalation: the user changes the configured binary because the service object grants them that right, or replaces the binary because its file or directory is writable, or plants a file earlier on an unquoted path because an intervening directory is writable, or rewrites the service's registry configuration because its key is weakly permissioned. At the next start, the privileged account runs the attacker's code. The bug is not the service running as system; it is a standard user holding a write that reaches what system executes. You find these by listing services and asking, for each, whether a non-admin can change the binary, the path, or the config.
When to use
- A Windows host runs services as a privileged account and you can enumerate their config and permissions.
- Service binaries, their directories, or unquoted service paths may be writable by a standard user.
- Service objects or their registry keys may grant configuration rights to non-administrators.
Scope check
Test service escalation only on hosts you own or are authorized to assess, on non-production or a snapshot, using a benign marker payload that proves execution as the privileged account rather than taking real action with it. A confirmed path yields code execution as a system account, so keep every probe within the authorized scope. If you can't name the authorization, stop.
The loop
- Establish the service's account and who can influence its target first. For each service, determine the account it runs as and whether a standard user holds any write that reaches what it executes: a service-object right to reconfigure it, write access to the binary or its directory, a writable directory earlier on an unquoted path, or write access to the service's registry key. This is the false-positive killer: a service whose binary, path, and configuration are writable only by administrators cannot be redirected by a standard user, however privileged the account it runs as. Name the specific write 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 · 142 lines · 174 tokens per session scan A ca0d76e76d67
hunting-windows-service-privilege-escalation is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 2,136 once invoked, about $0.0007 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.