gmail-automation
Warn
Audited by Snyk on Mar 6, 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). The skill explicitly fetches and ingests email bodies and attachments from external senders via required workflows (e.g., "Search and Filter Emails" and "Reply to a Thread" using GMAIL_FETCH_EMAILS with include_payload=true and GMAIL_GET_ATTACHMENT), which are untrusted/user-generated contents that could contain instructions influencing subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to the external MCP endpoint https://rube.app/mcp at runtime to fetch tool schemas (via RUBE_SEARCH_TOOLS) which directly control the agent's available instructions and behavior, making it a runtime dependency that can alter prompts.
Audit Metadata