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-ble-and-gatt-authorizationgit 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-ble-and-gatt-authorization)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ble-and-gatt-authorization"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ble-and-gatt-authorization/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-ble-and-gatt-authorization"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ble-and-gatt-authorization.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 | $0.00192 | $0.02239 |
| Opus 5.5 | $0.00077 | $0.00896 |
| Sonnet 5.5 | $0.00038 | $0.00448 |
| Haiku 4.5 | $0.00019 | $0.00224 |
Grade A, and why
auditing-ble-and-gatt-authorization 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing BLE and GATT authorization: the peripheral must enforce access, not the app
A Bluetooth Low Energy peripheral exposes its functionality as GATT characteristics that any peer in radio range can attempt to connect to and read or write, and the security question is entirely on the peripheral: does it enforce who may touch each characteristic, or does it assume the only client is its own trusted mobile app. The common failure is trusting the app. The app shows a login and a permission model, but the peripheral itself accepts reads and writes from any connected peer, so a peer that skips the app and talks to the GATT server directly performs the sensitive action, unlocking, dumping data, changing a setting, with no check. Pairing and bonding, which establish link encryption and a persistent trust relationship, are frequently not required, or fall back to the unauthenticated Just Works association that gives encryption without authenticating who is on the other end, so a sniffer or a man in the middle reads the traffic. And commands sent without authentication can be captured over the air and replayed. The audit connects to the peripheral as an arbitrary peer, enumerates its GATT attributes, and checks whether the device, not the app, enforces authorization on each. You audit this by talking to the GATT server directly and seeing what it lets an unauthorized peer do.
When to use
- A BLE peripheral (wearable, lock, sensor, medical or IoT device) exposes GATT characteristics a connected peer can read or write.
- Pairing or bonding may not be required, or may fall back to unauthenticated Just Works with no MITM protection.
- Authorization may be enforced in the mobile app rather than on the peripheral, or commands may be replayable.
Scope check
Test BLE devices only on hardware you own or are explicitly authorized to assess, in a controlled RF environment. Connecting to a peripheral, writing characteristics, and sniffing radio traffic exercise a real device and a shared spectrum, so use your own devices and never connect to, sniff, or actuate a device that is not yours or affect nearby devices. 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 · 151 lines · 192 tokens per session scan A 0588ed088619
auditing-ble-and-gatt-authorization is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 192 tokens to every session and 2,239 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.