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-secure-boot-and-firmware-signinggit 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-secure-boot-and-firmware-signing)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-secure-boot-and-firmware-signing"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-secure-boot-and-firmware-signing/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-secure-boot-and-firmware-signing"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-secure-boot-and-firmware-signing.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 | $0.00184 | $0.02175 |
| Opus 5 | $0.00092 | $0.01087 |
| Sonnet 5 | $0.00037 | $0.00435 |
| Haiku 4.5 | $0.00018 | $0.00217 |
Grade A, and why
auditing-secure-boot-and-firmware-signing 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing secure boot and firmware signing: does a verified signature gate every path to flash and boot
Firmware is the most durable place an attacker can land, and the whole defense is one property: an image is verified for authenticity before any code writes it to a boot slot or jumps to it. Auditing that property is a domination question, not a checklist. Trace the received image to every place it is committed, to flash or to the program counter, and ask whether a correct, enforced signature check stands on every path, over the exact bytes that reach the commit, against a key the attacker cannot influence. The common failures are all ways that check is absent, thrown away, checking the wrong thing, or checking the wrong bytes. You find them by reading the receipt-to-commit path, not by trusting that a function named verify verifies.
When to use
- Code receives a firmware image over an update channel and writes it to flash or activates a boot slot.
- A bootloader decides whether to execute an image at startup.
- You want to know whether an unsigned, tampered, or downgraded image can be flashed or booted.
Scope check
Audit firmware trust boundaries only on devices and code you own or are authorized to assess, and flash crafted images only to hardware in scope. A confirmed secure-boot bypass is persistent code execution, so treat it accordingly and coordinate. If you can't name the authorization, stop.
The loop
-
Map the receipt-to-commit paths. Find where an image arrives (an update channel, a port, a shared store) and every sink that commits it: a flash erase or write of a boot region, a call that marks a slot active or valid, and the branch to the image's entry point at boot. These sinks are what a verification must dominate, so enumerate them before judging any check.
-
Check that verification exists and its result is enforced. On each path, a signature check must run between receipt and commit. The bug is a commit with no check, a result computed and then discarded, a result defaulted to success and only set to failure on one branch, or an inverted test. A verify whose outcome does not gate the flash or the boot is not a check.
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 · 138 lines · 184 tokens per session scan A 2e9b903a13c3
auditing-secure-boot-and-firmware-signing is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 184 tokens to every session and 2,175 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. 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 citations…
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.
panguard
AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.