← Back to Skills Marketplace
S2-SP-OS Acoustic Radar
by
MilesXiang
· GitHub ↗
· v1.0.5
· MIT-0
121
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install s2-acoustic-perception
Description
S2-SP-OS Acoustic Radar. Edge-delegated zero-shot classification with Ephemeral Privacy and strict LAN-only network enforcement. / S2-SP-OS 语义声学雷达。本地边缘零样本分类，...
Usage Guidance
This skill appears coherent: it records a short (3s) audio slice and sends it to a local Edge Brain, enforcing private LAN IPs and requiring user consent. Before installing or running: 1) Confirm the Edge Brain service at the LAN address is fully under your control and audited—the skill cannot prevent a local server from forwarding data to the internet. 2) Isolate the Edge Brain on a network segment with blocked internet egress (firewall rules) if you need strong privacy guarantees. 3) Verify the Edge Brain implementation (the endpoint /api/v1/analyze) to ensure it doesn't store or exfiltrate raw audio. 4) Be aware the skill will access the system microphone—ensure user consent and consider a visible hardware/OS indicator. 5) Test in a controlled environment first (air-gapped or VLAN) to confirm behavior matches expectations.
Capability Analysis
Type: OpenClaw Skill
Name: s2-acoustic-perception
Version: 1.0.5
The skill bundle implements an acoustic radar that records audio and sends it to a local network endpoint for analysis. While `acoustic.py` includes security features like mandatory private IP checks (`ipaddress.is_private`) and `SKILL.md` emphasizes consent and privacy, the inherent capabilities of microphone access and network transmission of audio data are high-risk. The code appears aligned with its stated purpose of local-only acoustic perception, but the presence of these sensitive capabilities justifies a suspicious classification under the provided criteria for risky behaviors.
Capability Assessment
Purpose & Capability
Name/description (LAN-only acoustic radar, ephemeral audio) align with required binaries (python3) and included code. The code records a 3s audio slice, encodes it, and posts it to a local HTTP endpoint for classification—this is consistent with the stated Edge-Brain delegation design.
Instruction Scope
SKILL.md and code instruct the agent to record microphone audio (3s) and POST a Base64 WAV to http://<edge_ip>:8000/api/v1/analyze. That behaviour is within the declared purpose, but recording microphone input is inherently sensitive and the instructions rely on the Edge Brain being trustworthy and strictly LAN-bound. The SKILL.md requires explicit consent before recording, which the code enforces.
Install Mechanism
No install spec; instruction-only skill with a single Python file. Dependencies (sounddevice, numpy) are reasonable for local audio capture and processing. Nothing is downloaded from arbitrary URLs or installed silently.
Credentials
The skill requests no environment variables, no credentials, and no config paths. This is proportionate to its function. It does require microphone access (via local sounddevice) which is appropriate but sensitive.
Persistence & Privilege
always:false and no attempt to persist configuration or modify other skills. The code explicitly deletes the raw audio variables after sending (memzero pattern). It does not autonomously alter agent settings or write to disk.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install s2-acoustic-perception - After installation, invoke the skill by name or use
/s2-acoustic-perception - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
**LAN-only privacy enhancement and stricter network enforcement:**
- Now enforces cryptographic verification of the Edge IP to ensure only private LAN addresses (RFC 1918) are accepted.
- Public and non-LAN IP addresses are strictly blocked to guarantee data never leaves the local router.
- Updated documentation to reflect new firewall and privacy mechanisms.
- Maintains zero retention: raw audio is immediately discarded after semantic tagging.
v1.0.0
- Initial release of S2 Acoustic Perception (S2-SP-OS) Semantic Acoustic Radar.
- Provides zero-shot audio classification on the edge with strict ephemeral privacy—raw audio is instantly deleted after semantic tagging.
- Delegates AI inference to a trusted local LAN Edge Brain server.
- Semantic labels returned (e.g., "music", "dog_barking", "human_conversation") without storing or uploading raw audio.
- Selective acoustic evidence retention only for non-privacy events to support multimodal agent actions.
- Includes bilingual documentation and critical privacy-respecting usage instructions for agents.
Metadata
Frequently Asked Questions
What is S2-SP-OS Acoustic Radar?
S2-SP-OS Acoustic Radar. Edge-delegated zero-shot classification with Ephemeral Privacy and strict LAN-only network enforcement. / S2-SP-OS 语义声学雷达。本地边缘零样本分类，... It is an AI Agent Skill for Claude Code / OpenClaw, with 121 downloads so far.
How do I install S2-SP-OS Acoustic Radar?
Run "/install s2-acoustic-perception" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is S2-SP-OS Acoustic Radar free?
Yes, S2-SP-OS Acoustic Radar is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does S2-SP-OS Acoustic Radar support?
S2-SP-OS Acoustic Radar is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created S2-SP-OS Acoustic Radar?
It is built and maintained by MilesXiang (@spacesq); the current version is v1.0.5.
More Skills