Skills/ClawHub/join-meeting

join-meeting@1.1.15

CAUTION· static only

Publisher claims: "AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting," Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher johnpatternai · publishing for 136 daysInstalls 1,371Last detonated 2d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-12 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Coercive compliance language; Destructive file system command detected; Destructive file system command detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Process kill commandSKILL.md:1507 · Process kill command — agent can terminate processes4. On call.ended notification: stop Monitor, kill $BRIDGE_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Coercive compliance languageSKILL.md:1331 · Coercive compliance languageYou MUST follow THE CALL_LOOP algorithm (Method 1 event-driven loop, recommended — or Method 3 polling loop fallback) for theFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedscripts/node/register.js:89 · Destructive file system command detectedmessage: 'could not request code (check email format / connectivity)' }, 1);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/python/register.py:74 · Destructive file system command detected"message": "could not request code (check email format / connectivity)"}, 1)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:1297 · Process kill command — agent can terminate processeskill $SCREENSHARE_PID 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:1556 · Process kill command — agent can terminate processes4. After EXIT: kill bridge PID, delete events + commands files, fetch transcript if neededFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:1630 · Destructive file system command detectedrm /tmp/meeting-stdinFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈24,276 tok
1 file · 59 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim johnpatternai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim johnpatternaiPropose a patch to the maintainer