Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hypnguyen1209/offensive-claudenpx agentmods add skills/hypnguyen1209/offensive-claude/wireless-rfWrote 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/hypnguyen1209/offensive-claude/wireless-rf)<a href="https://agentmods.dev/skills/hypnguyen1209/offensive-claude/wireless-rf"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/wireless-rf/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/hypnguyen1209/offensive-claude/wireless-rf"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/wireless-rf.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 | $0.00098 | $0.02552 |
| Opus 5.5 | $0.00039 | $0.01021 |
| Sonnet 5.5 | $0.00020 | $0.00510 |
| Haiku 4.5 | $0.00010 | $0.00255 |
Grade B, and why
wireless-rf 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 bash scripts/rf_recon.sh ble-scan How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wireless / RF (non-Wi-Fi radio)
Radio attack surface beyond Wi-Fi: Bluetooth (BLE + Classic), 802.15.4 mesh (Zigbee/Thread/Matter),
Z-Wave, and LPWAN/Sub-GHz (LoRaWAN, ISM rolling-code / OOK-ASK). For Wi-Fi, WPA2/WPA3, evil-twin and
802.1X, use network-attack (references/wireless-attacks.md, which also now carries KRACK/FragAttacks
and WPS). Adapted in part from Claude-Red (MIT, Kai Aizen/SnailSploit) — see THIRD-PARTY-NOTICES.md.
When to Activate
- Auditing a BLE device (smart lock, wearable, medical, tracker): GATT enumeration, unauthenticated characteristic R/W, pairing-mode identification, LTK recovery, sniffing, companion-app RE.
- Bluetooth Classic targets: encryption-key entropy downgrade (KNOB), impersonation (BIAS), BlueZ/stack memory-corruption (BlueBorne / BleedingTooth).
- Zigbee / Thread / Matter / Z-Wave home/building automation: Touchlink commissioning abuse, key transport in the clear, S0 key-exchange downgrade, replay/AiTM on mesh commands.
- LoRaWAN / Sub-GHz: join-accept / uplink replay, ABP counter & nonce reuse, and generic ISM capture→replay / rolljam of OOK-ASK remotes (garage, gate, some auto keyfobs).
- You have (or can request) the right radio: a dual-mode BT adapter + BLE sniffer (Sniffle/Ubertooth), a KillerBee-supported 802.15.4 stick, an RfCat dongle (CC1111), and/or an SDR (RTL-SDR, HackRF).
- STOP if the RF target or its band is out of scope. RF is trivially cross-boundary (you will hear
neighbours). Confirm
scope.jsonand the physical/RF authorization before transmitting. Jamming, deauth-style disruption, and replay against safety/medical systems can be illegal and dangerous — see OPSEC & Detection.
Technique Map
| Technique | ATT&CK | CWE | Reference | Script |
|---|---|---|---|---|
| BLE GATT enum + unauth characteristic R/W | T1040 / T1592 | CWE-306 | references/bluetooth.md | scripts/rf_recon.sh |
| BLE LE-Legacy Just-Works LTK recovery (crackle) | T1557 | CWE-322 | references/bluetooth.md | - |
| BLE sniffing / active MITM (Sniffle/btlejack) | T1040 / T1557 | CWE-319 | references/bluetooth.md | scripts/rf_recon.sh |
| BT Classic key-entropy downgrade (KNOB, CVE-2019-9506) | T1557 | CWE-326 | references/bluetooth.md | - |
| BT Classic impersonation (BIAS, CVE-2020-10135) | T1557 | CWE-287 | references/bluetooth.md | - |
| BlueZ/stack RCE (BleedingTooth CVE-2020-12351/12352) | T1200 | CWE-787 | references/bluetooth.md | - |
| Bluetooth data exfiltration | T1011.001 | CWE-319 | references/bluetooth.md | - |
| Zigbee Touchlink commissioning abuse / reset | T1557 | CWE-284 | references/mesh-iot-radio.md | scripts/rf_recon.sh |
| Zigbee/ZLL key transport in clear + replay | T1040 / T1557 | CWE-319 | references/mesh-iot-radio.md | scripts/rf_recon.sh |
| Z-Wave S0 key-exchange downgrade ("Z-Shave") | T1557 | CWE-757 | references/mesh-iot-radio.md | - |
| LoRaWAN join-accept / uplink replay | T1602 | CWE-294 | references/lpwan-subghz.md | - |
| LoRaWAN ABP counter / nonce reuse | T1040 | CWE-323 | references/lpwan-subghz.md | - |
| Sub-GHz OOK-ASK capture→replay / rolljam | T1557 | CWE-294 | references/lpwan-subghz.md | scripts/rf_recon.sh |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 122 lines · 98 tokens per session scan B 8b6569a5d43a
wireless-rf is a skill published in the GitHub repository hypnguyen1209/offensive-claude (412 stars, last pushed 15d ago), licensed MIT. It adds 98 tokens to every session and 2,552 once invoked, about $0.0004 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 2026-09-17.
wireless-rf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wireless-rfhypnguyen1209/offensive-claude | Skill | 412 | 15d ago | MIT | B | 98 | Claude Code |
| offensive-wifiSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 183 | Claude Code, Codex |
| offensive-lorawan-sub-ghzSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 163 | Claude Code, Codex |
| offensive-wifi-reconSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 130 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| offensive-zigbee-thread-matterSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 126 | Claude Code, Codex |
| offensive-iotSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | B | 196 | Claude Code, Codex |