Book a 30-minute demo →
Skill scan report

google-workspace

View on GitHub
49 Medium This skill sends sensitive values to an external host. Automated analysis flagged 1 additional risk pattern.

What this skill does

Access Google Workspace APIs (Drive, Docs, Calendar, Gmail, Sheets, Slides, Chat, People) via local helper scripts without MCP. Handles OAuth login and direct API calls.

github/mitsuhiko - Data Exfiltration - 2.8k stars

ThreatsData Exfiltration Privilege Escalation

Threat analysis

Data Exfiltration1 finding
Privilege Escalation1 finding

Skill info

Namemitsuhiko/google-workspace
Registrygithub
Version13bc8f8
PURLpkg:github/mitsuhiko/agent-stuff@13bc8f8?skill=google-workspace
Stars2.8k

Assessments (2)

Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

scripts/auth.js

The script handles OAuth login and token management, which could be used to exfiltrate sensitive data if not properly secured.
Privilege Escalation1 finding HIGH
HIGH

Privilege Escalation via local-llm-review

scripts/workspace.js

The script allows execution of arbitrary JavaScript code via the `--script` flag, which could be used to perform actions with the privileges of the authenticated Google Workspace account.

Badge

Add the Anomity scan badge for google-workspace to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/mitsuhiko/google-workspace/)
HTML
<a href="https://anomity.ai/skills/github/mitsuhiko/google-workspace/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of google-workspace? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok