Skills/ClawHub/google-workspace-cli

google-workspace-cli@1.0.3

VERIFIED· install only

Publisher claims: "Automates Google Workspace from the terminal with the gws CLI: search, send, upload, export, share, and administer 20+ Google APIs. Use when driving Gmail, Drive, Calendar, Sheets, Docs, or the Admin SDK — bulk mail search and send, file sharing and export, event, user, and group management — when a Google API call fails with 403, invalid_grant, quota errors, or empty results, or when exposing Workspace operations as MCP tools. Not for Google Cloud infrastructure (gcloud) or local macOS mail and calendar apps." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ivangdavila · publishing for 275 daysInstalls 2,765Last detonated 4d ago
$clawhub install google-workspace-cli
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 95/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Authorization escalation languagememory-template.md:34 · Authorization escalation language · informational: not an instruction file- admin privileges available: yes | no | unknownFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageadmin.md:7 · Authorization escalation language · informational: not an instruction file- The executing account needs Workspace admin privileges — even read-only Directory calls 403 for regular users (`reason: insufficientPermissions` despite a perfectly scoped token).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagetroubleshooting.md:10 · Authorization escalation language · informational: not an instruction file…ope tier table in `auth-playbook.md`; on Admin APIs, also check the ACCOUNT has admin privileges (`admin.md`) | | `userRateLimitExceeded` / `rateLimitExceeded` | Quota, not pe…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,110 tok
1 file · 17 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.