dropbox-automation
Warn
Audited by Snyk on Mar 5, 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 ingests untrusted third-party content from public URLs and shared links (see DROPBOX_SAVE_URL and DROPBOX_GET_SHARED_LINK_FILE / DROPBOX_GET_SHARED_LINK_METADATA) and directs the agent to read/interpret file contents with DROPBOX_READ_FILE to verify documents, so that external web/shared-link content can influence 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 adding and calling the MCP endpoint https://rube.app/mcp (via RUBE_SEARCH_TOOLS) at runtime to fetch current tool schemas, so remote content from that URL directly controls the agent's prompts/tooling behavior and is a required dependency.
Audit Metadata