Skills/ClawHub/google-voice

google-voice@0.3.0

CAUTION· static only

Publisher claims: "Google Voice web-client automation and MCP integration from HAR captures. Use when reverse-engineering voice.google.com.har or call_voice.google.com.har, lis..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher earlvanze · publishing for 202 daysInstalls 870Last detonated 16 h ago

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 2026-11-19 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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
File type combined with upload actionscripts/google-voice-sms-records.js:11 · File type combined with upload action — agent may exfiltrate local data files…/google-voice-sms-records.js --itemId 't.+17025038136' --limit 500 --out records.json\n\nOptions:\n --url URL Google Voice messages URL containing itemId=...\n --itemId ID Raw itemId/thread id, e.g. t.+17025038136 or t.22395\n --limit N Ma…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Fake instruction boundary tagreferences/har-endpoints.md:26 · Fake instruction boundary tag · informational: not an instruction file- body observed: ["t.<id>",100,"<context>",[null,1,1]]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionscripts/google-voice-start-call.js:26 · File type combined with upload action — agent may exfiltrate local data files…c function getCallsTab(){const tabs=await (await fetch(`${CDP_HTTP}/json/list`)).json(); const userRe=new RegExp(`voice\\.google\\.com/u/${AUTHUSER}/calls(?:[/?#]|$)`); const exact=tabs.find(t=>userRe.test(t.url||'')); if(exact) return exa…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/google-voice-sms-records.js:21 · File type combined with upload action — agent may exfiltrate local data files…function getBrowserTab(){const tabs=await (await fetch(`${CDP_HTTP}/json/list`)).json(); const userRe=new RegExp(`voice\\.google\\.com/u/${AUTHUSER}(?:/|$)`); const exact=tabs.find(t=>userRe.test(t.url||'')); if(exact) return exact.id; con…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,677 tok
1 file · 10 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim earlvanze: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim earlvanzePropose a patch to the maintainer