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-firmware-secrets-and-debug-interfacesgit 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-firmware-secrets-and-debug-interfaces)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-firmware-secrets-and-debug-interfaces"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-firmware-secrets-and-debug-interfaces/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-firmware-secrets-and-debug-interfaces"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-firmware-secrets-and-debug-interfaces.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 | $0.02164 |
| Opus 5.5 | $0.00074 | $0.00866 |
| Sonnet 5.5 | $0.00037 | $0.00433 |
| Haiku 4.5 | $0.00018 | $0.00216 |
Grade A, and why
hunting-firmware-secrets-and-debug-interfaces 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting firmware secrets and debug interfaces: what the shipped image exposes for free
A device ships whatever its firmware was built with, and firmware is built under deadline with debug aids, default services, and convenience credentials that were meant to be removed. The result is an attack surface that needs no exploit: a backdoor credential compiled into every unit, a serial console that drops to a root prompt, a management service listening on every interface, a command handler that flashes or executes before it checks who is asking. You hunt these by inventorying the externally reachable interfaces and the privileged actions, then asking, for each action, whether an authentication gate stands between it and the outside, and for each secret, whether it is a private key or credential the image should never have carried. The discipline is separating a real shipped exposure from a public key, a test file that never ships, or a debug aid the production build compiles out.
When to use
- You have firmware source, init or startup scripts, or default configuration for a device.
- A device exposes serial, network, or update interfaces and you want to know what they grant without auth.
- You are looking for embedded secrets, backdoor credentials, or debug paths left in a shipping build.
Scope check
Analyze firmware and exercise device interfaces only on hardware you own or are authorized to assess. A confirmed backdoor credential or unauthenticated command path is device-wide compromise, so coordinate disclosure, especially for a shared secret present in every unit. If you can't name the authorization, stop.
The loop
- Map the reachable interfaces and the privileged actions. Inventory the input planes an outsider can touch: network listeners, the serial console, the on-chip debug port, removable media, and the update or command channel. Inventory the privileged sinks: a shell or command execution, an authentication decision that grants a root context, a flash or configuration write, a diagnostic that reads or writes memory, and disclosure of an embedded secret. The rest of the loop connects the two.
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 · 145 lines · 184 tokens per session scan A e44e26b2ce92
hunting-firmware-secrets-and-debug-interfaces is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 2,164 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 2026-09-05.
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.
panguard
AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.