helloleads-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 requires calling the external RUBE_SEARCH_TOOLS endpoint (via the MCP server at https://rube.app/mcp) and consuming the returned tool schemas and "recommended execution plans" at runtime, which are third-party-provided data the agent is expected to read and could carry indirect prompt-injection content.

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

  • Potentially malicious external URL detected (high risk: 0.90). Yes — the skill requires using https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL) to fetch tool schemas that drive agent behavior and to execute remote tools, so the remote endpoint can directly control prompts/instructions and run code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:22 AM