google-workspace
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly exposes tools that fetch and read user-generated content from Google Workspace (e.g., gmail.get/gmail.search, docs.getText, drive.downloadFile, sheets.getText, chat.getMessages), so the agent will ingest untrusted third‑party content that could contain instructions influencing its actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill config runs an external npm package at runtime via npx ("@presto-ai/google-workspace-mcp"), which will fetch and execute remote code when mcporter calls the tool and is a required dependency for the skill's operation.
Audit Metadata