formdesk-automation

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly directs the agent to query an external Rube MCP endpoint (https://rube.app/mcp) via RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS and to read returned tool schemas, execution plans, and auth links—arbitrary third-party content the agent will ingest and act on, enabling indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires configuring and using the MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS and RUBE_MULTI_EXECUTE_TOOL), and that server supplies tool schemas, execution plans and runs remote tools which directly control agent instructions and execute remote code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:31 PM