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-named-pipe-and-rpc-exposuregit 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-named-pipe-and-rpc-exposure)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-windows-named-pipe-and-rpc-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-windows-named-pipe-and-rpc-exposure/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-named-pipe-and-rpc-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-windows-named-pipe-and-rpc-exposure.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 | $0.00172 | $0.02090 |
| Opus 5.5 | $0.00069 | $0.00836 |
| Sonnet 5.5 | $0.00034 | $0.00418 |
| Haiku 4.5 | $0.00017 | $0.00209 |
Grade A, and why
auditing-windows-named-pipe-and-rpc-exposure 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing Windows named pipe and RPC exposure: when a local endpoint hands out privilege
A privileged Windows service often exposes an interface for others to talk to it: a named pipe, a remote procedure call endpoint, or a local COM server. Those interfaces are safe only when the service restricts who may connect and checks what each caller is authorized to ask for, and only when it does not blindly assume the identity of whoever connects. The exposure is an interface reachable by a lower-privileged caller that then performs a privileged action on the caller's behalf, or impersonates the connecting client in a way that lets a crafted caller flip the trust, or trusts caller-supplied input, a path, a command, a target, without checking the caller's authorization. In each case a standard user drives the privileged service into doing something the user could not do directly. The bug is a privileged action reachable across an inter-process boundary without the authorization that boundary should enforce. You audit these by listing each service's interfaces, who can reach them, and what each exposed operation does with the caller's request.
When to use
- A privileged service exposes a named pipe, RPC endpoint, or local COM server reachable by non-administrators.
- An exposed operation performs a privileged action or acts on caller-supplied input.
- A service impersonates connecting clients and a crafted caller may exploit that impersonation.
Scope check
Audit inter-process interfaces only on hosts you own or are authorized to assess, on non-production or a snapshot, using a benign proof that the privileged action was driven rather than performing a damaging one. A confirmed exposure lets a standard user drive privileged behavior, so keep every probe within scope. If you can't name the authorization, stop.
The loop
- Establish whether the interface restricts callers and authorizes each operation first. For each exposed interface, determine whether its permissions limit who may connect and whether the service checks the caller's authorization for each operation, or whether a lower-privileged caller can both reach it and invoke a privileged action. This is the false-positive killer: an interface restricted to administrators, or one that authorizes each operation against the caller, is not driven by a standard user however powerful its actions. Name the reachable operation and the missing check before crafting a call.
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 · 141 lines · 172 tokens per session scan A a87a23baf955
auditing-windows-named-pipe-and-rpc-exposure is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 2,090 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.