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-ota-and-firmware-update-channel-trustgit 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-ota-and-firmware-update-channel-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ota-and-firmware-update-channel-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ota-and-firmware-update-channel-trust/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-ota-and-firmware-update-channel-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ota-and-firmware-update-channel-trust.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 | $0.00199 | $0.02287 |
| Opus 5.5 | $0.00080 | $0.00915 |
| Sonnet 5.5 | $0.00040 | $0.00457 |
| Haiku 4.5 | $0.00020 | $0.00229 |
Grade A, and why
auditing-ota-and-firmware-update-channel-trust 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing OTA and firmware update channel trust: whatever a device installs, it runs forever
A firmware update is the most powerful thing that can happen to a device: whatever image it installs becomes the code it runs, persistently, with full control of the hardware. So the update channel is the highest-value boundary on the device, and the only thing standing between an attacker and permanent control is whether the device verifies an image before it installs it. The failures are a checklist of that verification. If the device does not verify a cryptographic signature over the image against a key it trusts, an attacker installs arbitrary firmware. If it fetches the image over an unauthenticated transport, an on-path attacker swaps the image in flight even if the server is honest. If it does not enforce version monotonicity, an attacker rolls the device back to an older, still-signed image with known vulnerabilities and re-exploits it. If it trusts an update server or manifest URL without authenticating it, an attacker who controls or spoofs that endpoint feeds it a malicious image. And an unencrypted image leaks embedded secrets and hands a reverse engineer the code. The audit follows an update from where the device learns of it to where it installs it and checks that the image is signature-verified, transport-authenticated, and version-monotonic before it ever runs. You audit this by trying to get the device to install an image it should refuse.
When to use
- A device fetches and installs firmware or application updates in the field (IoT, embedded, router, wearable).
- The update image may not be signature-verified, or may be fetched over an unauthenticated transport.
- The device may allow rollback to older signed images, or trust an update server or manifest URL without authentication.
Scope check
Test update channels only on devices and infrastructure you own or are authorized to assess, in a controlled environment. Feeding a device a crafted image or intercepting its update traffic can brick hardware and exercise a real install path, so use your own devices and test servers and never push firmware to or intercept updates for a device that is not yours. If you can't name the authorization, stop.
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 · 149 lines · 199 tokens per session scan A b39b13446650
auditing-ota-and-firmware-update-channel-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 2,287 once invoked, about $0.0008 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.