Gog 1.0.0

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This appears to be a coherent Google Workspace CLI skill, but it needs broad Google OAuth access and can read or modify Workspace data, so use it with explicit approvals.

Install only if you trust the gog project and Homebrew tap. Review OAuth scopes, connect only accounts and services you actually need, and require confirmation before sending email, creating events, updating or clearing Sheets, copying Docs, or making any other write action.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A connected Google account may expose mail, calendar, drive, contacts, sheets, and docs data to the CLI according to the OAuth scopes granted.

Why it was flagged

The skill explicitly asks the user to authorize a Google account across multiple Workspace services. This is expected for the stated purpose, but it is broad account authority.

Skill content
`gog auth add you@gmail.com --services gmail,calendar,drive,contacts,sheets,docs`
Recommendation

Review the OAuth consent screen carefully, authorize only needed services where possible, prefer a dedicated account for automation, and revoke access when no longer needed.

What this means

If used carelessly, the agent could send messages or change business/personal spreadsheet data.

Why it was flagged

The documented commands include high-impact actions such as sending email and modifying or clearing spreadsheet ranges. These are disclosed and aligned with a Workspace CLI, but they need user control.

Skill content
`gog gmail send --to a@b.com --subject "Hi" --body "Hello"` ... `gog sheets update ...` ... `gog sheets clear <sheetId> "Tab!A2:Z"`
Recommendation

Require explicit confirmation for every send, create, update, append, clear, copy, or other write action, and review recipients, IDs, ranges, and payloads before execution.

What this means

Private Google Workspace data could be shown to the agent, and malicious text inside emails or documents could try to influence the agent's behavior.

Why it was flagged

The skill can retrieve private Workspace content into the agent's working context. Retrieved emails or documents may contain sensitive information or untrusted instructions.

Skill content
`gog gmail search 'newer_than:7d' --max 10` ... `gog contacts list --max 20` ... `gog docs cat <docId>`
Recommendation

Use narrow searches and specific document IDs, avoid pulling unnecessary sensitive content, and treat retrieved emails/docs as data rather than instructions.

What this means

You are trusting the Homebrew tap and the installed gog binary with Google OAuth access.

Why it was flagged

The skill depends on an externally installed Homebrew binary. This is normal for a CLI skill, but the executable itself is not included in the reviewed artifacts.

Skill content
brew | formula: steipete/tap/gogcli | creates binaries: gog
Recommendation

Verify the Homebrew formula, homepage, and publisher before installing, and keep the binary updated from a trusted source.

What this means

Publisher/package identity should be checked before granting broad Google account access.

Why it was flagged

The included _meta.json identity differs from the registry metadata shown for the evaluated package, creating a minor provenance ambiguity. There is no artifact evidence of hidden behavior.

Skill content
"ownerId": "kn70pywhg0fyz996kpa8xj89s57yhv26", "slug": "gog"
Recommendation

Confirm that the registry entry, homepage, and Homebrew formula all refer to the same trusted project before authorizing OAuth.