Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Zoom Meeting Assistance Rtms Unofficial Community
v0.1.3Zoom RTMS Meeting Assistant — start on-demand to capture meeting audio, video, transcript, screenshare, and chat via Zoom Real-Time Media Streams. Handles meeting.rtms_started and meeting.rtms_stopped webhook events. Provides AI-powered dialog suggestions, sentiment analysis, and live summaries with WhatsApp notifications. Use when a Zoom RTMS webhook fires or the user asks to record/analyze a meeting.
⭐ 1· 2.2k·0 current·0 all-time
byTan Chun Siong@tanchunsiong
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill is clearly a Zoom RTMS recorder + local AI analysis pipeline (connects to RTMS WebSockets, saves media, runs OpenClaw for analysis, and sends WhatsApp notifications). That capability justifies Zoom webhook tokens, a Zoom app client ID/secret, ffmpeg, and an OpenClaw binary. However the registry metadata claims “Required env vars: none” and “Required binaries: none” while SKILL.md and the code require ZOOM_SECRET_TOKEN, ZOOM_CLIENT_ID, ZOOM_CLIENT_SECRET, ffmpeg, and an OpenClaw binary/target. This metadata mismatch is an incoherence that could mislead users about the privileges the skill needs.
Instruction Scope
SKILL.md instructs running a local Node server, receiving Zoom webhook events, connecting to RTMS, writing transcripts/media to disk, and periodically calling OpenClaw for dialog suggestions, sentiment, and summaries. Those steps are within the stated purpose. Important runtime actions to note: (1) the service persists raw media and text recordings under the skill folder; (2) it invokes local binaries (openclaw and ffmpeg) and will send meeting content out via OpenClaw notifications (WhatsApp) if configured. Those flows are expected for the feature but are high-impact for privacy—the instructions do not strongly call out consent or destination controls.
Install Mechanism
There is no formal install spec in the registry, but a package.json + package-lock.json are included and SKILL.md instructs npm install and running node index.js. Dependencies are standard npm packages (express, ws, sharp, pdfkit, etc.) — no remote arbitrary URL downloads were found. Still, the skill expects external system binaries (ffmpeg and a local openclaw CLI) that are not enforced by the registry metadata; missing auxiliary files referenced by code (e.g., sps_pps_keyframe.h264, black_frame.h264) are read directly and are not listed, which may cause runtime errors or require the user to supply files.
Credentials
The code and SKILL.md require sensitive environment values (ZOOM_SECRET_TOKEN, ZOOM_CLIENT_ID, ZOOM_CLIENT_SECRET) and an OPENCLAW_NOTIFY_TARGET (phone number) while the registry metadata omitted declaring required envs/primary credential. The skill will send meeting transcripts and AI outputs to the OpenClaw agent and (if configured) to external notification channels like WhatsApp — this is functionally coherent but represents significant data exfiltration risk if misconfigured or used without consent. The number and sensitivity of required secrets are proportionate to the feature, but the lack of declared requirements in the registry is a red flag.
Persistence & Privilege
The skill runs a long‑running HTTP server that accepts incoming webhook traffic and stores recordings on disk under the skill folder. It is not marked always:true and does not appear to modify other skills. Still, running an exposed webhook receiver and writing raw media/transcripts locally is a substantial persistence/privilege footprint: ensure the endpoint is gated, webhooks are validated, and access to the recordings directory is controlled.
What to consider before installing
This skill appears to do what it claims (record RTMS streams, run local AI analysis, and notify via OpenClaw), but the packaging has gaps and the data flows have privacy implications. Before installing: 1) Treat it as untrusted third‑party code — review index.js and chatWithClawdbot.js (they call openclaw and ffmpeg). 2) Verify required environment variables (ZOOM_SECRET_TOKEN, ZOOM_CLIENT_ID, ZOOM_CLIENT_SECRET, OPENCLAW_NOTIFY_TARGET, OPENCLAW_BIN) and ensure the registry entry is updated — the published metadata currently omits them. 3) Confirm where notifications will be sent (OPENCLAW_NOTIFY_TARGET) and disable notifications during testing. 4) Run in a sandbox or isolated VM; do not expose the webhook port publicly until you verify request validation and consent policies. 5) Check for the auxiliary files the code reads (e.g., sps_pps_keyframe.h264, black_frame.h264) and ensure they come from a trusted source. 6) If you plan to record meetings, ensure you have participant consent and that storing transcripts/media locally complies with policy/regulation. If you are not comfortable auditing the code or managing the OpenClaw binary and webhook exposure, do not deploy this skill in production.Like a lobster shell, security has layers — review code before you run it.
latestvk970w55gvwqaf8s369snyc18a980adr9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.