opengraph-io-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 automates the "opengraph_io" toolkit via Rube MCP and instructs executing tools (e.g., RUBE_MULTI_EXECUTE_TOOL) using discovered tool schemas—an operation that inherently fetches and interprets OpenGraph metadata from arbitrary public URLs/web pages (third‑party, user-provided content), exposing the agent to untrusted external content.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires runtime interaction with the Rube MCP endpoint https://rube.app/mcp (via RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL) to fetch tool schemas/instructions and invoke remote tools, which directly control prompts/behavior and execute remote actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:19 PM