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 Miosa-osa/OSA --skill offensive-bluetooth-blegit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/offensive-bluetooth-ble)<a href="https://agentmods.dev/skills/miosa-osa/osa/offensive-bluetooth-ble"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-bluetooth-ble/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/miosa-osa/osa/offensive-bluetooth-ble"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-bluetooth-ble.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 | $0.00122 | $0.01992 |
| Opus 5.5 | $0.00049 | $0.00797 |
| Sonnet 5.5 | $0.00024 | $0.00398 |
| Haiku 4.5 | $0.00012 | $0.00199 |
Grade B, and why
offensive-bluetooth-ble scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo bettercap -eval "ble.recon on; events.show 60; ble.show" How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bluetooth Low Energy (BLE) Attacks
BLE devices communicate via GATT — a hierarchy of services, characteristics, and descriptors. Many devices treat the BLE link itself as the trust boundary, exposing privileged operations on characteristics readable/writable from any nearby device.
Quick Workflow
- Discover and enumerate the device's GATT tree
- Test every characteristic for read/write/notify without authentication
- Inspect pairing method — Just Works = no MITM protection
- If Just Works, MITM the pairing to capture / inject
- Reverse the companion app for proprietary command formats
Discovery + GATT Enumeration
# bettercap (interactive)
sudo bettercap -eval "ble.recon on; events.show 60; ble.show"
# Or, attach to a known-MAC device
sudo bettercap -eval "ble.recon on; ble.enum AA:BB:CC:DD:EE:FF"
# bluetoothctl
bluetoothctl
> scan on
> connect AA:BB:CC:DD:EE:FF
> menu gatt
> list-attributes
# gatttool (deprecated but still works)
gatttool -b AA:BB:CC:DD:EE:FF -I
> connect
> primary # list services
> char-desc # list characteristics
> char-read-uuid <uuid>
> char-write-req <handle> <hex>
GATT services use 16-bit UUIDs for SIG-defined services (battery, heart rate) and 128-bit UUIDs for vendor-defined ones. Custom 128-bit UUIDs are where vendor-specific commands live — that's your attack surface.
Characteristic Auth-Free Read/Write
Test every characteristic flagged read/write/notify:
# Read all readable characteristics
for h in $(gatttool -b <MAC> --primary | awk '{print $5}'); do
echo "=== Handle $h ==="
gatttool -b <MAC> --char-read --handle=$h
done
# Write to writable characteristics with crafted values
gatttool -b <MAC> --char-write-req --handle=0x0010 --value=0x01
Common findings on consumer BLE devices:
- Door locks:
unlockcharacteristic accepts any write (no auth) - Smart bulbs: brightness/color writeable from any peer
- Wearables: PIN/lock-state readable
- BLE beacons: configurable from any peer (rebrand attacks)
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 · 235 lines · 122 tokens per session scan B c207c97b8cf9
offensive-bluetooth-ble is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 122 tokens to every session and 1,992 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
openhue
Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes.
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
gap
Program robots with GaP (graph-as-policy) — compile natural-language tasks into typed, verified robot skill graphs and run them on simulators or real robots. Use when the user mentions GaP or graph-as-policy, robot manipulation, robot skills, robot tools or capabilities, skill registries, open-robot-skills, LIBERO or…