bonsai-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: 0.90). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the external Rube MCP (e.g., https://rube.app/mcp) to retrieve tool schemas, recommended execution plans and metadata which the agent is expected to read and act on at runtime, exposing it to untrusted third‑party content.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires runtime interaction with the MCP server at https://rube.app/mcp (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS), which returns tool schemas, recommended execution plans and arguments that directly control agent instructions and are a required dependency for workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:42 AM